arXiv Machine Learning
Unknown Unknowns: Do Hidden Intentions in LLMs Evade Detection?
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 10
Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring
arXiv:2607. 08066v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces can surface misaligned or deceptive behavior.
arXiv AI
Jun 29
AI Snitches Get Glitches: Towards Evading Agentic Surveillance
arXiv:2606. 25836v2 Announce Type: replace Abstract: To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs.
arXiv AI
Sep 23
Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection
arXiv:2609.24801v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation throu...
arXiv AI
Jun 17
Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing
arXiv:2606. 17478v1 Announce Type: cross Abstract: As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern.
arXiv Machine Learning
Aug 4
Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors
arXiv:2608. 00566v1 Announce Type: new Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare.
arXiv AI
Aug 24
Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.