arXiv AI
The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 26
The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming
Automatic red teaming increasingly relies on large language models (LLMs) to iteratively diagnose failed attacks and propose improved adversarial prompts or injections. Although prior work strengthens...
arXiv Computation and Language
Sep 16
Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion
The paper introduces the SAST-IR framework to evaluate large language models’ robustness against persuasion attacks in a memory‑less setting, revealing a flaw called "Refusal Inertia" that masks true vulnerability. Using the CP‑Agent and a custom CounterFact‑Strict dataset, the authors demonstrate that simple, diverse attack strategies achieve a 96% success rate, while complex attacks often trigger defensive compliance. The study highlights severe brittleness in current state‑of‑the‑art models when deprived of conversation history.
arXiv AI
Sep 30
CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...
arXiv AI
Aug 12
REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems
arXiv:2608. 10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks.
arXiv AI
Sep 1
SIR: Self-improving Red-teaming for Compute Use Agents
arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal...
arXiv AI
Jun 24
AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability
arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.