Control Tax: The Price of Keeping AI in Check

• URL: http://arxiv.org/abs/2506.05296v2
• Date: Sat, 14 Jun 2025 18:09:16 GMT
• Title: Control Tax: The Price of Keeping AI in Check
• Abstract summary: We introduce the notion of Control tax -- the operational and financial cost of integrating control measures into AI pipelines.<n>We conduct comprehensive evaluations of state-of-the-art language models in adversarial settings.<n>We provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies.
• Score: 22.94651464417764
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid integration of agentic AI into high-stakes real-world applications requires robust oversight mechanisms. The emerging field of AI Control (AIC) aims to provide such an oversight mechanism, but practical adoption depends heavily on implementation overhead. To study this problem better, we introduce the notion of Control tax -- the operational and financial cost of integrating control measures into AI pipelines. Our work makes three key contributions to the field of AIC: (1) we introduce a theoretical framework that quantifies the Control Tax and maps classifier performance to safety assurances; (2) we conduct comprehensive evaluations of state-of-the-art language models in adversarial settings, where attacker models insert subtle backdoors into code while monitoring models attempt to detect these vulnerabilities; and (3) we provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies that balance safety and cost-effectiveness while accounting for practical constraints like auditing budgets. Our framework enables practitioners to make informed decisions by systematically connecting safety guarantees with their costs, advancing AIC through principled economic feasibility assessment across different deployment contexts.

Related papers

• From Frontier to Shadow AI: A Simmering Threat to Assurance and Security in Critical Infrastructure [8.167474882691755]
  We present the first empirical study of shadow AI in critical infrastructure environments.<n>We analyse how shadow AI manifests in practice, how it interacts with existing technical and governance controls, and the resulting security, assurance, and compliance risks.
  arXiv  Detail & Related papers  (2026-05-23T07:21:08Z)
• TRUST: A Framework for Decentralized AI Service v.0.1 [47.384270414446604]
  Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification.<n>We introduce TRUST (Transparent, Robust, and Unified Services for Trustworthy AI), a decentralized framework with three innovations.<n>We prove a Safety-Profitability Theorem ensuring honest auditors profit while malicious actors incur losses.
  arXiv  Detail & Related papers  (2026-04-29T19:32:58Z)
• Hardware-Level Governance of AI Compute: A Feasibility Taxonomy for Regulatory Compliance and Treaty Verification [0.0]
  This paper bridges the gap between AI governance and computer engineering by proposing a taxonomy of 20 hardware-level governance mechanisms.<n>For each mechanism, we provide a technical description, a feasibility rating, and an identification of adversarial vulnerabilities.
  arXiv  Detail & Related papers  (2026-04-06T14:26:14Z)
• Overcoming the Incentive Collapse Paradox [1.529342790344802]
  As AI accuracy improves, sustaining positive human effort requires unbounded payments.<n>We propose a sentinel-auditing payment mechanism that enforces a strictly positive and controllable level of human effort.<n> Experiments demonstrate improved cost-error tradeoffs relative to standard active learning and auditing-only baselines.
  arXiv  Detail & Related papers  (2026-03-27T23:37:37Z)
• SAGE-LLM: Towards Safe and Generalizable LLM Controller with Fuzzy-CBF Verification and Graph-Structured Knowledge Retrieval for UAV Decision [46.089736018739295]
  Large Language Models (LLM) lack domain-specific UAV control knowledge and formal safety assurances.<n>This paper proposes a train-free two-layer decision architecture based on LLMs, integrating high-level safety planning with low-level precise control.
  arXiv  Detail & Related papers  (2026-02-27T06:41:04Z)
• Conformal Thinking: Risk Control for Reasoning on a Compute Budget [60.65072883773352]
  Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases.<n>We re-frame the budget setting problem as risk control, limiting the error rate while minimizing compute.<n>Our framework introduces an upper threshold that stops reasoning when the model is confident and a novel lower threshold that preemptively stops unsolvable instances.
  arXiv  Detail & Related papers  (2026-02-03T18:17:22Z)
• Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique [0.0]
  This study presents a decision-negative, human-in-the-loop agentic system that incorporates an adversarial self-critique mechanism.<n>Within this system, a critic agent challenges the primary agent's conclusions prior to submitting recommendations to human reviewers.<n>The research develops a formal taxonomy of failure modes to characterize potential errors by decision-negative agents.
  arXiv  Detail & Related papers  (2026-01-21T05:51:27Z)
• Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions [51.56484100374058]
  Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes.<n>This gap, driven by mutually cognitive biases in both humans and artificial intelligence (AI) systems, threatens the defensibility of valuations and sustainability of investments in the sector.<n>This report describes a framework emerging from systematic qualitative assessment across 7 frontier-grade LLMs and 3 market-facing venture vignettes under time pressure.
  arXiv  Detail & Related papers  (2025-11-10T22:24:21Z)
• Agentic AI for Financial Crime Compliance [0.0]
  This paper presents the design and deployment of an agentic AI system for financial crime compliance (FCC) in digitally native financial platforms.<n>The contribution includes a reference architecture, a real-world prototype, and insights into how Agentic AI can reconfigure under regulatory constraints.
  arXiv  Detail & Related papers  (2025-09-16T14:53:51Z)
• Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance [211.5823259429128]
  We propose a comprehensive framework integrating technical and societal dimensions, structured around three interconnected pillars: Intrinsic Security, Derivative Security, and Social Ethics.<n>We identify three core challenges: (1) the generalization gap, where defenses fail against evolving threats; (2) inadequate evaluation protocols that overlook real-world risks; and (3) fragmented regulations leading to inconsistent oversight.<n>Our framework offers actionable guidance for researchers, engineers, and policymakers to develop AI systems that are not only robust and secure but also ethically aligned and publicly trustworthy.
  arXiv  Detail & Related papers  (2025-08-12T09:42:56Z)
• Efficient Agents: Building Effective Agents While Reducing Cost [48.65558640786415]
  Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks.<n>This work presents the first systematic study of the efficiency-effectiveness trade-off in modern agent systems.
  arXiv  Detail & Related papers  (2025-07-24T17:56:51Z)
• Watermarking Without Standards Is Not AI Governance [46.71493672772134]
  We argue that current implementations risk serving as symbolic compliance rather than delivering effective oversight.<n>We propose a three-layer framework encompassing technical standards, audit infrastructure, and enforcement mechanisms.
  arXiv  Detail & Related papers  (2025-05-27T18:10:04Z)
• In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI [93.33036653316591]
  We call for three interventions to advance system safety.<n>First, we propose using standardized AI flaw reports and rules of engagement for researchers.<n>Second, we propose GPAI system providers adopt broadly-scoped flaw disclosure programs.<n>Third, we advocate for the development of improved infrastructure to coordinate distribution of flaw reports.
  arXiv  Detail & Related papers  (2025-03-21T05:09:46Z)
• Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models [1.0088912103548195]
  Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by decomposing complex problems into step-by-step solutions.<n>Current CoT disclosure policies vary widely across different models in visibility, API access, and pricing strategies, lacking a unified policy framework.<n>We propose a tiered-access policy framework that balances transparency, accountability, and security by tailoring CoT availability to academic, business, and general users.
  arXiv  Detail & Related papers  (2025-03-14T19:54:18Z)
• Enhancing the Efficiency and Accuracy of Underlying Asset Reviews in Structured Finance: The Application of Multi-agent Framework [3.022596401099308]
  We show that AI can automate the verification of information between loan applications and bank statements effectively. This research highlights AI's potential to minimize manual errors and streamline due diligence, suggesting a broader application of AI in financial document analysis and risk management.
  arXiv  Detail & Related papers  (2024-05-07T13:09:49Z)
• Proof-of-Learning with Incentive Security [15.219480512237682]
  Most concurrent blockchain systems rely heavily on the Proof-of-Work (PoW) or Proof-of-Stake (PoS) mechanisms for decentralized consensus and security assurance.<n>PoUW seeks to employ challenges of practical significance as PoW, thereby imbuing energy consumption with tangible value.<n>We introduce the concept of incentive-security that incentivizes rational provers to behave honestly for their best interest, bypassing the existing hardness to design a PoL mechanism with computational efficiency, a provable incentive-security guarantee and controllable difficulty.
  arXiv  Detail & Related papers  (2024-04-13T13:18:40Z)
• A Framework for Assurance Audits of Algorithmic Systems [2.2342503377379725]
  We propose the criterion audit as an operationalizable compliance and assurance external audit framework. We argue that AI audits should similarly provide assurance to their stakeholders about AI organizations' ability to govern their algorithms in ways that harms and uphold human values. We conclude by offering a critical discussion on the benefits, inherent limitations, and implementation challenges of applying practices of the more mature financial auditing industry to AI auditing.
  arXiv  Detail & Related papers  (2024-01-26T14:38:54Z)
• AI auditing: The Broken Bus on the Road to AI Accountability [1.9758196889515185]
  "AI audit" ecosystem is muddled and imprecise, making it difficult to work through various concepts and map out the stakeholders involved in the practice. First, we taxonomize current AI audit practices as completed by regulators, law firms, civil society, journalism, academia, consulting agencies. We find that only a subset of AI audit studies translate to desired accountability outcomes.
  arXiv  Detail & Related papers  (2024-01-25T19:00:29Z)
• A Survey and Comparative Analysis of Security Properties of CAN Authentication Protocols [92.81385447582882]
  The Controller Area Network (CAN) bus leaves in-vehicle communications inherently non-secure. This paper reviews and compares the 15 most prominent authentication protocols for the CAN bus. We evaluate protocols based on essential operational criteria that contribute to ease of implementation.
  arXiv  Detail & Related papers  (2024-01-19T14:52:04Z)
• Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory [46.85103495283037]
  We propose a new approach to apply verification methods from control theory to learned value functions. We formalize original theorems that establish links between value functions and control barrier functions. Our work marks a significant step towards a formal framework for the general, scalable, and verifiable design of RL-based control systems.
  arXiv  Detail & Related papers  (2023-06-06T21:41:31Z)
• Auditing large language models: a three-layered approach [0.0]
  Large language models (LLMs) represent a major advance in artificial intelligence (AI) research. LLMs are also coupled with significant ethical and social challenges. Previous research has pointed towards auditing as a promising governance mechanism.
  arXiv  Detail & Related papers  (2023-02-16T18:55:21Z)
• Towards a multi-stakeholder value-based assessment framework for algorithmic systems [76.79703106646967]
  We develop a value-based assessment framework that visualizes closeness and tensions between values. We give guidelines on how to operationalize them, while opening up the evaluation and deliberation process to a wide range of stakeholders.
  arXiv  Detail & Related papers  (2022-05-09T19:28:32Z)
• Explanations of Machine Learning predictions: a mandatory step for its application to Operational Processes [61.20223338508952]
  Credit Risk Modelling plays a paramount role. Recent machine and deep learning techniques have been applied to the task. We suggest to use LIME technique to tackle the explainability problem in this field.
  arXiv  Detail & Related papers  (2020-12-30T10:27:59Z)
• Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning [100.73223416589596]
  We propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations. A new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-06T06:28:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.