arXiv:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.
By Shubham Kumar, Narendra Ahuja
arXiv:2605.09504v3 Announce Type: replace-cross
Abstract: We show that the instruments used to measure AI offensive capability fail in two ways: (i) they overstate harm, and (ii) they credit the mode...
By Michael Alexander Riegler, Finn Schwall, Annika Willoch Olstad, Birk Sebastian Frostelid Torpmann-Hagen, Sushant Gautam, Klas H. Pettersen, Inga Str\"umke
arXiv:2605. 17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces.
By Qiqi Liu, Runhan Song, Shilin Ye
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.
By Harry Owiredu-Ashley
arXiv:2610.27620v1 Announce Type: cross
Abstract: Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authori...
By Anmol Pandey, Aditya Jain, Liang Chen, Carsten Maple
Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an agent's Model Context Protocol (MCP) tool set, each engineered to probe one specific tool-selection weakness.
arXiv:2608. 04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why.
By Atul Anand, Sourav Chattaraj
arXiv:2610.34167v1 Announce Type: new
Abstract: Tool-using language model agents are usually evaluated by whether they finish the user's task. That metric misses a common failure: an agent can comple...
By Jiaju Huang, Shaobin Chen, Xinglong Liang, Xinyu Ma, Hao Yang, Wei Ke, Tao Tan, Yue Sun
The paper introduces ‘Fool’s Gold’, a defensive deception technique for open‑weight language models that hardens them against safety‑removal attacks. By training decoy responses within a differentiable simulation of the attack, the method poisons the payoff of stripped refusal mechanisms, producing confident but falsified answers to hazardous requests while preserving benign behavior. Experiments on seven models (9B‑122B) show that 51‑90% of attacked‑state responses become decoys, with the defense accounting for 27‑84% of this effect, and that the defended 122B model remains within benign‑behavior budgets.
By Mark Russinovich
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov
arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.
By Subhadip Mitra
arXiv:2609.27900v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinat...
By Zonghao Ying, Jiaqi Yan, Huize Luo, Quanchen Zou, Aishan Liu, Xianglong Liu