AI Threat, Cyber Threat, and Planning for Check and Analysis

Fashionable synthetic intelligence (AI) methods pose new sorts of dangers, and many of those are each consequential and never effectively understood. Regardless of this, many AI-based methods are being accelerated into deployment. That is creating nice urgency to develop efficient take a look at and analysis (T&E) practices for AI-based methods.

This weblog submit explores potential methods for framing T&E practices on the premise of a holistic method to AI danger. In creating such an method, it’s instructive to construct on classes discovered within the a long time of battle to develop analogous practices for modeling and assessing cyber danger. Cyber danger assessments are imperfect and proceed to evolve, however they supply vital profit nonetheless. They’re strongly advocated by the Cybersecurity and Infrastructure Safety Company (CISA), and the prices and advantages of assorted approaches are a lot mentioned within the enterprise media. About 70% of inside audits for big corporations embrace cyber danger assessments, as do mandated stress checks for banks.

Threat modeling and assessments for AI are much less effectively understood from each technical and authorized views, however there’s pressing demand from each enterprise adopters and vendor suppliers nonetheless. The industry-led Coalition for Safe AI launched in July 2024 to assist advance {industry} norms round enhancing the safety of recent AI implementations. The NIST AI Threat Administration Framework (RMF) is resulting in proposed practices. Methodologies based mostly on the framework are nonetheless a piece in progress, with unsure prices and advantages, and so AI danger assessments are much less usually utilized than cyber danger assessments.

Threat modeling and evaluation are essential not solely in guiding T&E, but in addition in informing engineering practices, as we’re seeing with cybersecurity engineering and within the rising apply of AI engineering. AI engineering, importantly, encompasses not simply particular person AI parts in methods but in addition the general design of resilient AI-based methods, together with the workflows and human interactions that allow operational duties.

AI danger modeling, even in its present nascent stage, can have helpful affect in each T&E and AI engineering practices, starting from general design selections to particular danger mitigation steps. AI-related weaknesses and vulnerabilities have distinctive traits (see examples within the prior weblog posts), however additionally they overlap with cyber dangers. AI system parts are software program elements, in any case, so that they usually have vulnerabilities unrelated to their AI performance. Nonetheless, their distinctive and sometimes opaque options, each inside the fashions and within the surrounding software program buildings, could make them particularly enticing to cyber adversaries.

That is the third installment in a four-part collection of weblog posts targeted on AI for important methods the place trustworthiness—based mostly on checkable proof—is important for operational acceptance. The 4 elements are comparatively impartial of one another and handle this problem in levels:

• Half 1: What are applicable ideas of safety and security for contemporary neural-network-based AI, together with machine studying (ML) and generative AI, reminiscent of giant language fashions (LLMs)? What are the AI-specific challenges in creating secure and safe methods? What are the boundaries to trustworthiness with fashionable AI, and why are these limits elementary?
• Half 2: What are examples of the sorts of dangers particular to fashionable AI, together with dangers related to confidentiality, integrity, and governance (the CIG framework), with and with out adversaries? What are the assault surfaces, and what sorts of mitigations are presently being developed and employed for these weaknesses and vulnerabilities?
• Half 3 (this half): How can we conceptualize T&E practices applicable to fashionable AI? How, extra typically, can frameworks for danger administration (RMFs) be conceptualized for contemporary AI analogous to these for cyber danger? How can a apply of AI engineering handle challenges within the close to time period, and the way does it work together with software program engineering and cybersecurity issues?
• Half 4: What are the advantages of trying past the purely neural-network fashions of recent AI in direction of hybrid approaches? What are present examples that illustrate the potential advantages, and the way, trying forward, can these approaches advance us past the elemental limits of recent AI? What are prospects within the close to and longer phrases for hybrid AI approaches which might be verifiably reliable and that may help extremely important functions?

Assessments for Practical and High quality Attributes

Practical and high quality assessments assist us acquire confidence that methods will carry out duties appropriately and reliably. Correctness and reliability are usually not absolute ideas, nevertheless. They have to be framed within the context of supposed functions for a element or system, together with operational limits that have to be revered. Expressions of intent essentially embody each performance—what the system is meant to perform—and system qualities—how the system is meant to function, together with safety and reliability attributes. These expressions of intent, or methods specs, could also be scoped for each the system and its function in operations, together with expectations relating to stressors reminiscent of adversary threats.

Fashionable AI-based methods pose vital technical challenges in all these facets, starting from expressing specs to acceptance analysis and operational monitoring. What does it imply, for instance, to specify intent for a skilled ML neural community, past inventorying the coaching and testing knowledge?

We should contemplate, in different phrases, the conduct of a system or an related workflow underneath each anticipated and sudden inputs, the place these inputs could also be notably problematic for the system. It’s difficult, nevertheless, even to border the query of the way to specify behaviors for anticipated inputs that aren’t precisely matched within the coaching set. A human observer could have an intuitive notion of similarity of latest inputs with coaching inputs, however there isn’t any assurance that this aligns with the precise that includes—the salient parameter values—inside to a skilled neural community.

We should, moreover, contemplate assessments from a cybersecurity perspective. An knowledgeable and motivated attacker could intentionally manipulate operational inputs, coaching knowledge, and different facets of the system improvement course of to create circumstances that impair right operation of a system or its use inside a workflow. In each circumstances, the absence of conventional specs muddies the notion of “right” conduct, additional complicating the event of efficient and reasonably priced practices for AI T&E. This specification problem suggests one other commonality with cyber danger: facet channels, that are potential assault surfaces which might be unintentional to implementation and that might not be a part of a specification.

Three Dimensions of Cyber Threat

This alignment within the rising necessities for AI-focused T&E with strategies for cybersecurity analysis is clear when evaluating NIST’s AI danger administration playbook with the extra mature NIST Cybersecurity Framework, which encompasses an enormous variety of strategies. On the danger of oversimplification, we will usefully body these strategies within the context of three dimensions of cyber danger.

• Risk issues the potential entry and actions of adversaries in opposition to the system and its broader operational ecosystem.
• Consequence pertains to the magnitude of impression on a company or mission ought to an assault on a system achieve success.
• Vulnerability pertains to intrinsic design weaknesses and flaws within the implementation of a system.

Each menace and consequence carefully depend upon the operational context of use of that system, although they are often largely extrinsic to the system itself. Vulnerability is attribute of the system, together with its structure and implementation. The modeling of assault floor—apertures right into a system which might be uncovered to adversary actions—encompasses menace and vulnerability, as a result of entry to vulnerabilities is a consequence of operational surroundings. It’s a notably helpful component of cyber danger evaluation.

Cyber danger modeling is in contrast to conventional probabilistic actuarial danger modeling. That is primarily because of the typically nonstochastic nature of every of the three dimensions, particularly when threats and missions are consequential. Risk, for instance, is pushed by the operational significance of the system and its workflow, in addition to potential adversary intents and the state of their information. Consequence, equally, is set by selections relating to the location of a system in operational workflows. Changes to workflows—and human roles—is a mitigation technique for the consequence dimension of danger. Dangers will be elevated when there are hidden correlations. For cyber danger, these may embrace widespread parts with widespread vulnerabilities buried in provide chains. For AI danger, these may embrace widespread sources inside giant our bodies of coaching knowledge. These correlations are a part of the explanation why some assaults on LLMs are transportable throughout fashions and suppliers.

CISA, MITRE, OWASP, and others provide handy inventories of cyber weaknesses and vulnerabilities. OWASP, CISA, and the Software program Engineering Institute additionally present inventories of secure practices. Most of the generally used analysis standards derive, in a bottom-up method, from these inventories. For weaknesses and vulnerabilities at a coding stage, software program improvement environments, automated instruments, and continuous-integration/continuous-delivery (CI/CD) workflows usually embrace evaluation capabilities that may detect insecure coding as builders kind it or compile it into executable elements. Due to this quick suggestions, these instruments can improve productiveness. There are a lot of examples of standalone instruments, reminiscent of from Veracode, Sonatype, and Synopsys.

Importantly, cyber danger is only one component within the general analysis of a system’s health to be used, whether or not or not it’s AI-based. For a lot of built-in hardware-software methods, acceptance analysis will even embrace, for instance, conventional probabilistic reliability analyses that mannequin (1) sorts of bodily faults (intermittent, transient, everlasting), (2) how these faults can set off inside errors in a system, (3) how the errors could propagate into numerous sorts of system-level failures, and (4) what sorts of hazards or harms (to security, safety, efficient operation) may lead to operational workflows. This latter method to reliability has an extended historical past, going again to John von Neumann’s work within the Fifties on the synthesis of dependable mechanisms from unreliable elements. Curiously, von Neumann cites analysis in probabilistic logics that derive from fashions developed by McCulloch and Pitts, whose neural-net fashions from the Nineteen Forties are precursors of the neural-network designs central to fashionable AI.

Making use of These Concepts to Framing AI Threat

Framing AI danger will be thought of as an analog to framing cyber danger, regardless of main technical variations in all three facets—menace, consequence, and vulnerability. When adversaries are within the image, AI penalties can embrace misdirection, unfairness and bias, reasoning failures, and so forth. AI threats can embrace tampering with coaching knowledge, patch assaults on inputs, immediate and fine-tuning assaults, and so forth. Vulnerabilities and weaknesses, reminiscent of these inventoried within the CIG classes (see Half 2), typically derive from the intrinsic limitations of the structure and coaching of neural networks as statistically derived fashions. Even within the absence of adversaries, there are a selection of penalties that may come up because of the specific weaknesses intrinsic to neural-network fashions.

From the angle of conventional danger modeling, there’s additionally the problem, as famous above, of sudden correlations throughout fashions and platforms. For instance, there will be related penalties attributable to diversely sourced LLMs sharing basis fashions or simply having substantial overlap in coaching knowledge. These sudden correlations can thwart makes an attempt to use strategies reminiscent of variety by design as a method to enhance general system reliability.

We should additionally contemplate the particular attribute of system resilience. Resilience is the capability of a system that has sustained an assault or a failure to nonetheless proceed to function safely, although maybe in a degraded method. This attribute is typically referred to as swish degradation or the flexibility to function by way of assaults and failures. Normally, this can be very difficult, and sometimes infeasible, so as to add resilience to an present system. It’s because resilience is an emergent property consequential of system-level architectural selections. The architectural objective is to cut back the potential for inside errors—triggered by inside faults, compromises, or inherent ML weaknesses—to trigger system failures with pricey penalties. Conventional fault-tolerant engineering is an instance of design for resilience. Resilience is a consideration for each cyber danger and AI danger. Within the case of AI engineering, resilience will be enhanced by way of system-level and workflow-level design selections that, for instance, restrict publicity of weak inside assault surfaces, reminiscent of ML inputs, to potential adversaries. Such designs can embrace imposing energetic checking on inputs and outputs to neural-network fashions constituent to a system.

As famous in Half 2 of this weblog collection, a further problem to AI resilience is the problem (or maybe incapacity) to unlearn coaching knowledge. Whether it is found {that a} subset of coaching knowledge has been used to insert a vulnerability or again door into the AI system, it turns into a problem to take away that skilled conduct from the AI system. In apply, this continues to stay troublesome and will necessitate retraining with out the malicious knowledge. A associated difficulty is the other phenomenon of undesirable unlearning—referred to as catastrophic forgetting—which refers to new coaching knowledge unintentionally impairing the standard of predictions based mostly on earlier coaching knowledge.

Trade Considerations and Responses Concerning AI Threat

There’s a broad recognition amongst mission stakeholders and corporations of the dimensionality and problem of framing and evaluating AI danger, regardless of speedy progress in AI-related enterprise actions. Researchers at Stanford College produced a 500-page complete enterprise and technical evaluation of AI-related actions that states that funding for generative AI alone reached $25.2 billion in 2023. That is juxtaposed in opposition to a seemingly limitless stock of new sorts of dangers related to ML and generative AI. Illustrative of it is a joint research by the MIT Sloan Administration Evaluation and the Boston Consulting Group that signifies that corporations are having to increase organizational danger administration capabilities to deal with AI-related dangers, and that this example is prone to persist because of the tempo of technological advance. A separate survey indicated that solely 9 % of corporations stated they had been ready to deal with the dangers. There are proposals to advance obligatory assessments to guarantee guardrails are in place. That is stimulating the service sector to reply, with impartial estimates of a marketplace for AI mannequin danger administration price $10.5 billion by 2029.

Enhancing Threat Administration inside AI Engineering Apply

Because the neighborhood advances danger administration practices for AI, it is vital keep in mind each the varied facets of danger, as illustrated within the earlier submit of this collection, and likewise the feasibility of the completely different approaches to mitigation. It’s not a simple course of: Evaluations have to be performed at a number of ranges of abstraction and construction in addition to a number of levels within the lifecycles of mission planning, structure design, methods engineering, deployment, and evolution. The various ranges of abstraction could make this course of troublesome. On the highest stage, there are workflows, human-interaction designs, and system architectural designs. Selections made relating to every of those facets have affect over the chance parts: attractiveness to menace actors, nature and extent of penalties of potential failures, and potential for vulnerabilities attributable to design selections. Then there’s the architecting and coaching for particular person neural-network fashions, the fine-tuning and prompting for generative fashions, and the potential publicity of assault surfaces of those fashions. Beneath this are, for instance, the particular mathematical algorithms and particular person traces of code. Lastly, when assault surfaces are uncovered, there will be dangers related to selections within the supporting computing firmware and {hardware}.

Though NIST has taken preliminary steps towards codifying frameworks and playbooks, there stay many challenges to creating widespread parts of AI engineering apply—design, implementation, T&E, evolution—that might evolve into helpful norms—and vast adoption pushed by validated and usable metrics for return on effort. Arguably, there’s a good alternative now, whereas AI engineering practices are nonetheless nascent, to shortly develop an built-in, full-lifecycle method that {couples} system design and implementation with a shift-left T&E apply supported by proof manufacturing. This contrasts with the apply of safe coding, which was late-breaking within the broader software program improvement neighborhood. Safe coding has led to efficient analyses and instruments and, certainly, many options of recent memory-safe languages. These are nice advantages, however safe coding’s late arrival has the unlucky consequence of an infinite legacy of unsafe and sometimes weak code that could be too burdensome to replace.

Importantly, the persistent problem of instantly assessing the safety of a physique of code hinders not simply the adoption of greatest practices but in addition the creation of incentives for his or her use. Builders and evaluators make selections based mostly on their sensible expertise, for instance, recognizing that guided fuzzing correlates with improved safety. In lots of of those circumstances probably the most possible approaches to evaluation relate to not the precise diploma of safety of a code base. As an alternative they deal with the extent of compliance with a technique of making use of numerous design and improvement strategies. Precise outcomes stay troublesome to evaluate in present apply. As a consequence, adherence to codified practices such because the safe improvement lifecycle (SDL) and compliance with the Federal Info Safety Modernization Act (FISMA) has grow to be important to cyber danger administration.

Adoption will also be pushed by incentives which might be unrelated however aligned. For instance, there are intelligent designs for languages and instruments that improve safety however whose adoption is pushed by builders’ curiosity in enhancing productiveness, with out in depth coaching or preliminary setup. One instance from internet improvement is the open supply TypeScript language as a secure various to JavaScript. TypeScript is almost an identical in syntax and execution efficiency, but it surely additionally helps static checking, which will be performed virtually instantly as builders kind in code, somewhat than surfacing a lot later when code is executing, maybe in operations. Builders could thus undertake TypeScript on the premise of productiveness, with safety advantages alongside for the trip.

Potential optimistic alignment of incentives shall be essential for AI engineering, given the problem of creating metrics for a lot of facets of AI danger. It’s difficult to develop direct measures for normal circumstances, so we should additionally develop helpful surrogates and greatest practices derived from expertise. Surrogates can embrace diploma of adherence to engineering greatest practices, cautious coaching methods, checks and analyses, selections of instruments, and so forth. Importantly, these engineering strategies embrace improvement and analysis of structure and design patterns that allow creation of extra reliable methods from much less reliable parts.

The cyber danger realm gives a hybrid method of surrogacy and selective direct measurement through the Nationwide Info Assurance Partnership (NIAP) Frequent Standards: Designs are evaluated in depth, however direct assays on lower-level code are performed by sampling, not comprehensively. One other instance is the extra broadly scoped Constructing Safety In Maturity Mannequin (BSIMM) undertaking, which features a technique of ongoing enhancement to its norms of apply. In fact, any use of surrogates have to be accompanied by aggressive analysis each to repeatedly assess validity and to develop direct measures.

Analysis Practices: Trying Forward

Classes for AI Pink Teaming from Cyber Pink Teaming

The October 2023 Government Order 14110 on the Protected, Safe, and Reliable Growth and Use of Synthetic Intelligence highlights using pink teaming for AI danger analysis. Within the navy context, a typical method is to make use of pink groups in a capstone coaching engagement to simulate extremely succesful adversaries. Within the context of cyber dangers or AI dangers, nevertheless, pink groups will usually have interaction all through a system lifecycle, from preliminary mission scoping, idea exploration, and architectural design by way of to engineering, operations, and evolution.

A key query is the way to obtain this sort of integration when experience is a scarce useful resource. One of many classes of cyber pink teaming is that it’s higher to combine safety experience into improvement groups—even on a part-time or rotating foundation—than to mandate consideration to safety points. Research recommend that this may be efficient when there are cross-team safety specialists instantly collaborating with improvement groups.

For AI pink groups, this implies that bigger organizations may keep a cross-team physique of specialists who perceive the stock of potential weaknesses and vulnerabilities and the state of play relating to measures, mitigations, instruments, and related practices. These specialists could be briefly built-in into agile groups so they may affect operational selections and engineering selections. Their targets are each to maximise advantages from use of AI and likewise to reduce dangers by way of making selections that help assured T&E outcomes.

There could also be classes for the Division of Protection, which faces specific challenges in integrating AI danger administration practices into the methods engineering tradition, as famous by the Congressional Analysis Service.

AI pink groups and cyber pink groups each handle the dangers and challenges posed by adversaries. AI pink groups should additionally handle dangers related to AI-specific weaknesses, together with all three CIG classes of weaknesses and vulnerabilities: confidentiality, integrity, and governance. Pink workforce success will depend upon full consciousness of all dimensions of danger in addition to entry to applicable instruments and capabilities to help efficient and reasonably priced assessments.

On the present stage of improvement, there’s not but a standardized apply for AI pink groups. Instruments, coaching, and actions haven’t been totally outlined or operationalized. Certainly, it may be argued that the authors of Government Order 14110 had been sensible to not await technical readability earlier than issuing the EO! Defining AI pink workforce ideas of operation is an monumental, long-term problem that mixes technical, coaching, operational, coverage, market, and plenty of different facets, and it’s prone to evolve quickly because the expertise evolves. The NIST RMF is a crucial first step in framing this dimensionality.

Potential Practices for AI Threat

A broad variety of technical practices is required for the AI pink workforce toolkit. Analogously with safety and high quality evaluations, AI stakeholders can anticipate to depend on a mixture of course of compliance and product examination. They will also be introduced with numerous sorts of proof starting from full transparency with detailed technical analyses to self-attestation by suppliers, with selections difficult by enterprise issues regarding mental property and legal responsibility. This extends to produce chain administration for built-in methods, the place there could also be various ranges of transparency. Legal responsibility is a altering panorama for cybersecurity and, we will anticipate, additionally for AI.

Course of compliance for AI danger can relate, for instance, to adherence to AI engineering practices. These practices can vary from design-level evaluations of how AI fashions are encapsulated inside a methods structure to compliance with greatest practices for knowledge dealing with and coaching. They’ll additionally embrace use of mechanisms for monitoring behaviors of each methods and human operators throughout operations. We be aware that process-focused regimes in cyber danger, such because the extremely mature physique of labor from NIST, can contain tons of of standards that could be utilized within the improvement and analysis of a system. Programs designers and evaluators should choose and prioritize among the many many standards to develop aligned mission assurance methods.

We will anticipate that with a maturing of strategies for AI functionality improvement and AI engineering, proactive practices will emerge that, when adopted, are inclined to lead to AI-based operational capabilities that reduce key danger attributes. Direct evaluation and testing will be complicated and dear, so there will be actual advantages to utilizing validated process-compliance surrogates. However this may be difficult within the context of AI dangers. For instance, as famous in Half 1 of this collection, notions of take a look at protection and enter similarity standards acquainted to software program builders don’t switch effectively to neural-network fashions.

Product examination can pose vital technical difficulties, particularly with rising scale, complexity, and interconnection. It could possibly additionally pose business-related difficulties, attributable to problems with mental property and legal responsibility. In cybersecurity, sure facets of merchandise are actually turning into extra readily accessible as areas for direct analysis, together with use of exterior sourcing in provide chains and the administration of inside entry gateways in methods. That is partly a consequence of a cyber-policy focus that advances small increments of transparency, what we may name translucency, reminiscent of has been directed for software program payments of supplies (SBOM) and 0 belief (ZT) architectures. There are, after all, tradeoffs regarding transparency of merchandise to evaluators, and it is a consideration in using open supply software program for mission methods.

Satirically, for contemporary AI methods, even full transparency of a mannequin with billions of parameters could not yield a lot helpful info to evaluators. This pertains to the conflation of code and knowledge in fashionable AI fashions famous on the outset of this collection. There may be vital analysis, nevertheless, in extracting associational maps from LLMs by patterns of neuron activations. Conversely, black field AI fashions could reveal much more about their design and coaching than their creators could intend. The perceived confidentiality of coaching knowledge will be damaged by way of mannequin inversion assaults for ML and memorized outputs for LLMs.

To be clear, direct analysis of neural-network fashions will stay a big technical problem. This provides extra impetus to AI engineering and the applying of applicable rules to the event and analysis of AI-based methods and the workflows that use them.

Incentives

The proliferation of process- and product-focused standards, as simply famous, generally is a problem for leaders searching for to maximise profit whereas working affordably and effectively. The balancing of selections will be extremely specific to the operational circumstances of a deliberate AI-based system in addition to to the technical selections made relating to the interior design and improvement of that system. That is one purpose why incentive-based approaches can usually be fascinating over detailed process-compliance mandates. Certainly, incentive-based approaches can provide extra levels of freedom to engineering leaders, enabling danger discount by way of diversifications to operational workflows in addition to to engineered methods.

Incentives will be each optimistic and detrimental, the place optimistic incentives might be provided, for instance, in improvement contracts, when assertions regarding AI dangers are backed with proof or accountability. Proof may relate to a variety of early AI-engineering selections starting from methods structure and operational workflows to mannequin design and inside guardrails.

An incentive-based method additionally has the benefit of enabling assured methods engineering—based mostly on rising AI engineering rules—to evolve particularly contexts of methods and missions at the same time as we proceed to work to advance the event of extra normal strategies. The March 2023 Nationwide Cybersecurity Technique highlights the significance of accountability relating to knowledge and software program, suggesting one essential attainable framing for incentives. The problem, after all, is the way to develop dependable frameworks of standards and metrics that may inform incentives for the engineering of AI-based methods.

Here’s a abstract of classes for present analysis apply for AI dangers:

1. Prioritize mission-relevant dangers. Based mostly on the particular mission profile, determine and prioritize potential weaknesses and vulnerabilities. Do that as early as attainable within the course of, ideally earlier than methods engineering is initiated. That is analogous to the Division of Protection technique of mission assurance.
2. Establish risk-related targets. For these dangers deemed related, determine targets for the system together with related system-level measures.
3. Assemble the toolkit of technical measures and mitigations. For those self same dangers, determine technical measures, potential mitigations, and related practices and instruments. Monitor the event of rising technical capabilities.
4. Regulate top-level operational and engineering selections. For the upper precedence dangers, determine changes to first-order operational and engineering selections that might result in possible danger reductions. This may embrace adapting operational workflow designs to restrict potential penalties, for instance by elevating human roles or lowering assault floor on the stage of workflows. It may additionally embrace adapting system architectures to cut back inside assault surfaces and to constrain the impression of weaknesses in embedded ML capabilities.
5. Establish strategies to evaluate weaknesses and vulnerabilities. The place direct measures are missing, surrogates have to be employed. These strategies may vary from use of NIST-playbook-style checklists to adoption of practices reminiscent of DevSecOps for AI. It may additionally embrace semi-direct evaluations on the stage of specs and designs analogous to Frequent Standards.
6. Search for aligned attributes. Search optimistic alignments of danger mitigations with presumably unrelated attributes that provide higher measures. For instance, productiveness and different measurable incentives can drive adoption of practices favorable to discount of sure classes of dangers. Within the context of AI dangers, this might embrace use of design patterns for resilience in technical architectures as a method to localize any hostile results of ML weaknesses.

The subsequent submit on this collection examines the potential advantages of trying past the purely neural-network fashions in direction of approaches that hyperlink neural-network fashions with symbolic strategies. Put merely, the objective of those hybridizations is to realize a type of hybrid vigor that mixes the heuristic and linguistic virtuosity of recent neural networks with the verifiable trustworthiness attribute of many symbolic approaches.