arXiv:2510. 14207v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm.
arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).
arXiv:2609.13579v1 Announce Type: new Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understandin...
arXiv:2609.38389v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear...
The paper introduces TIER, a Threat Implicitness Benchmark designed to evaluate large language model (LLM) safety behaviors across four risk domains and four threat levels, ranging from explicit harmful requests to sophisticated jailbreaks. Responses are scored on a six-label behavior scale by two independent LLM judges. Experiments on six open-weight LLMs reveal that safety behaviors change gradually with threat level, contextual prompts produce the most varied responses, and jailbreaks expose significant robustness gaps, underscoring the importance of behavior-aware safety evaluation.
arXiv:2602. 16346v4 Announce Type: replace-cross Abstract: LLM-based agents execute real-world workflows via tools and memory.
The paper introduces BLUEPRINT, a safety‑evaluation framework that separates a factorized social‑influence strategy space from WORLDVIEWSIM, a cross‑turn situational context module. Using Monte Carlo Tree Search, it optimizes turn‑level combinations of 18 theory‑grounded influence factors across a four‑turn trajectory, achieving near‑ceiling ASR on six frontier models with an average of only 2.46 queries. The study reveals that model‑specific vulnerabilities arise from distinct influence factors and strategy transitions, yet all models share a recovery pathway that shifts toward concrete, executable task framing to escape hard‑refusal states, highlighting the importance of monitoring how dialogue state makes unsafe requests appear actionable.
arXiv:2608. 10530v1 Announce Type: cross Abstract: Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory.
arXiv:2608.23028v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in education, healthcare, policy advising, and other interactive settings, where users engage th...
arXiv:2510. 17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate.
arXiv:2609.06972v1 Announce Type: cross Abstract: LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection...
The paper introduces ADVERSA, an automated red‑teaming framework that evaluates large language model safety over multiple turns by tracking continuous compliance trajectories instead of binary jailbreak outcomes. Using a fine‑tuned 70B attacker model and a structured 5‑point rubric, the authors conduct controlled experiments on three frontier victim models, measuring guardrail degradation and judge reliability through a triple‑judge consensus. Results show a 26.7% jailbreak rate with most breaches occurring early, and the study documents inter‑judge agreement, attacker drift, and attacker refusals as key factors affecting safety assessment.
arXiv:2606. 04867v1 Announce Type: new Abstract: As AI companion platforms such as Replika and Character.