QSAF: A Novel Mitigation Framework for Cognitive Degradation in Agentic AI

• URL: http://arxiv.org/abs/2507.15330v1
• Date: Mon, 21 Jul 2025 07:41:58 GMT
• Title: QSAF: A Novel Mitigation Framework for Cognitive Degradation in Agentic AI
• Abstract summary: We introduce Cognitive Degradation as a novel vulnerability class in agentic AI systems.<n>These failures originate internally, arising from memory starvation, planner recursion, context flooding, and output suppression.<n>To address this class of failures, we introduce the Qorvex Security AI Framework for Behavioral & Cognitive Resilience.
• Score: 2.505520948667288
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We introduce Cognitive Degradation as a novel vulnerability class in agentic AI systems. Unlike traditional adversarial external threats such as prompt injection, these failures originate internally, arising from memory starvation, planner recursion, context flooding, and output suppression. These systemic weaknesses lead to silent agent drift, logic collapse, and persistent hallucinations over time. To address this class of failures, we introduce the Qorvex Security AI Framework for Behavioral & Cognitive Resilience (QSAF Domain 10), a lifecycle-aware defense framework defined by a six-stage cognitive degradation lifecycle. The framework includes seven runtime controls (QSAF-BC-001 to BC-007) that monitor agent subsystems in real time and trigger proactive mitigation through fallback routing, starvation detection, and memory integrity enforcement. Drawing from cognitive neuroscience, we map agentic architectures to human analogs, enabling early detection of fatigue, starvation, and role collapse. By introducing a formal lifecycle and real-time mitigation controls, this work establishes Cognitive Degradation as a critical new class of AI system vulnerability and proposes the first cross-platform defense model for resilient agentic behavior.

Related papers

• TrojanWorld: Backdooring World-Model Agents via Imagination Steering [65.38754125569848]
  TrojanWorld is a backdoor framework for world-model agents that induces attacker-specified behavior by steering internal imagination.<n>Under trigger activation, TrojanWorld achieves a target-action deviation as low as 0.026 while retaining at least 98.8% of the corresponding clean performance.
  arXiv  Detail & Related papers  (2026-09-07T05:14:10Z)
• The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI [0.0]
  This study formalizes the threat model for persistence-based attacks and the threat of Dynamics Blindness.<n>The transition from stateless generative models in artificial intelligence to stateful, autonomous agents represents an architectural evolution.<n>This study synthesizes a defense-in-depth landscape, categorizing emerging frameworks such as diagnostic trajectory guardrails (AgentDoG), formal temporal verification (Agent-C), immunological memory consensus (A-MemGuard) and hardware-anchored trust via GPU-based Trusted Environments (TEEs) and Zero-Trust memory architectures.
  arXiv  Detail & Related papers  (2026-07-20T22:50:33Z)
• Operational Hallucination and Safety Drift in AI Agents [0.3823356975862005]
  Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.<n>This paper empirically characterizes two observed failure modes across multiple state-of-the-art LLMs: Safety Drift and Operational Hallucination.<n>We propose an Action-Aware Supervision Layer - a lightweight, plug-and-play architectural blueprint incorporating intent-action consistency checks, state tracking, and forced termination primitives.
  arXiv  Detail & Related papers  (2026-07-20T17:01:50Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections [57.64370755825839]
  Self-evolving agents update their internal state across sessions, often by writing and reusing long-term memory.<n>We study this risk and formalize a persistent attack we call a Zombie Agent.<n>We present a black-box attack framework that uses only indirect exposure through attacker-controlled web content.
  arXiv  Detail & Related papers  (2026-02-17T15:28:24Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models [0.2291770711277359]
  Large Language Models (LLMs) are rapidly transitioning from conversational assistants to autonomous agents embedded in critical organizational functions.<n>This paper presents the first systematic application of the Cybersecurity Psychology Framework (cpf), a 100-indicator taxonomy of human psychological vulnerabilities, to non-human cognitive agents.
  arXiv  Detail & Related papers  (2025-12-30T13:25:36Z)
• Cognitive Control Architecture (CCA): A Lifecycle Supervision Framework for Robustly Aligned AI Agents [1.014002853673217]
  LLM agents are vulnerable to Indirect Prompt Injection (IPI) attacks.<n>IPI attacks hijack agent behavior by polluting external information sources.<n>We propose the Cognitive Control Architecture (CCA), a holistic framework achieving full-lifecycle cognitive supervision.
  arXiv  Detail & Related papers  (2025-12-07T08:11:19Z)
• AI Deception: Risks, Dynamics, and Controls [153.71048309527225]
  This project provides a comprehensive and up-to-date overview of the AI deception field.<n>We identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception.<n>We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment.
  arXiv  Detail & Related papers  (2025-11-27T16:56:04Z)
• Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System [2.5145802129902664]
  The MAESTRO framework was used to expose, evaluate, and eliminate vulnerabilities of agentic AI.<n>The prototype agent system was constructed and implemented, using Python, LangChain, and telemetry in WebSockets.
  arXiv  Detail & Related papers  (2025-08-12T00:14:12Z)
• A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents [45.53643260046778]
  Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents.<n>These large-model agents mark a paradigm shift from static inference systems to interactive, memory-augmented entities.
  arXiv  Detail & Related papers  (2025-06-30T13:34:34Z)
• Avoiding Death through Fear Intrinsic Conditioning [48.07595141865156]
  We introduce an intrinsic reward function inspired by early amygdala development and produce this intrinsic reward through a novel memory-augmented neural network architecture.<n>We show how this intrinsic motivation serves to deter exploration of terminal states and results in avoidance behavior similar to fear conditioning observed in animals.
  arXiv  Detail & Related papers  (2025-06-05T19:24:51Z)
• DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents [28.294322726282896]
  Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling.<n>This paper presents the first systematic investigation of memory-based vulnerabilities in LLM-powered recommender agents.<n>We propose a novel black-box attack framework named DrunkAgent, which crafts semantically meaningful adversarial triggers.
  arXiv  Detail & Related papers  (2025-03-31T07:35:40Z)
• CRAFT: Characterizing and Root-Causing Fault Injection Threats at Pre-Silicon [4.83186491286234]
  This work presents a comprehensive methodology for conducting controlled fault injection attacks at the pre-silicon level.<n>As the driving application, we use the clock glitch attacks in AI/ML applications for critical misclassification.
  arXiv  Detail & Related papers  (2025-03-05T20:17:46Z)
• Honest to a Fault: Root-Causing Fault Attacks with Pre-Silicon RISC Pipeline Characterization [4.83186491286234]
  This study aims to characterize and diagnose the impact of faults within the RISC-V instruction set and pipeline stages, while tracing fault propagation from the circuit level to the AI/ML application software.<n>This analysis resulted in discovering a novel vulnerability through controlled clock glitch parameters, specifically targeting the RISC-V decode stage.
  arXiv  Detail & Related papers  (2025-03-05T20:08:12Z)
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases [73.04652687616286]
  We propose AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance.
  arXiv  Detail & Related papers  (2024-07-17T17:59:47Z)
• Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems [67.01132165581667]
  We propose to enable high-level reasoning in AI systems by integrating cognitive architectures with external neuro-symbolic components. We illustrate a hybrid framework centered on ACT-R and we discuss the role of generative models in recent and future applications.
  arXiv  Detail & Related papers  (2023-11-13T21:20:17Z)
• The Feasibility and Inevitability of Stealth Attacks [63.14766152741211]
  We study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence systems. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself.
  arXiv  Detail & Related papers  (2021-06-26T10:50:07Z)
• Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and concept drift [62.997667081978825]
  Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security. In this paper, we present a solution to effectively mitigate this attack by improving the detection process and efficiently leveraging human expertise.
  arXiv  Detail & Related papers  (2020-01-13T13:54:36Z)

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.