arXiv Computation and Language
SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
Hugging Face Trending Papers
Oct 26
SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy
Existing jailbreak attackers fall into two classes: static planners fix their single- or multi-turn adversarial plans in advance, remaining simple but losing sight of the victim's replies, wasting tur...
arXiv AI
Oct 26
$M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process
$M^3$ is an automated red‑teaming framework that models multi‑turn jailbreaking as a finite‑horizon Markov Decision Process. It lets an attacker LLM interact with a target LLM while using a state LLM to maintain a compact internal state. Across two benchmarks and six target models, $M^3$ outperforms existing methods, boosting attack success rates by up to 53% at five turns and improving consistency and risk escalation metrics.
arXiv AI
Aug 18
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
arXiv:2608. 15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails.
arXiv AI
Jun 2
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
arXiv:2603. 24511v2 Announce Type: replace-cross Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations.
arXiv Machine Learning
Sep 14
SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
SaFeR-Steer is a progressive multi‑turn alignment framework that uses staged synthetic bootstrapping and tutor‑in‑the‑loop GRPO to train a single student model against adaptive, on‑policy attacks. It introduces Trajectory‑Consistent Summative Reward (TCSR) to ensure that low‑quality turns impact the overall trajectory reward. The authors release the STEER dataset and demonstrate that SaFeR‑Steer significantly improves safety and helpfulness on both single‑turn and multi‑turn benchmarks for Qwen2.5‑VL models.
arXiv AI
Jul 21
Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
arXiv:2607. 18063v1 Announce Type: cross Abstract: LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation.