5 papers
Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training
Avidan Shah, Jannik Brinkmann, Rico Angell
As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection…
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
Andy Han, Kristina Fujimoto, Avidan Shah +5
Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promi…
Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
Xinpeng Wang, Nitish Joshi, Barbara Plank +2
Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior…
Jailbreak Transferability Emerges from Shared Representations
Rico Angell, Jannik Brinkmann, He He
Jailbreak transferability is the surprising phenomenon when an adversarial attack compromising one model also elicits harmful responses from other models. Despite widespread demons…
Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors
Chen Yueh-Han, Nitish Joshi, Yulin Chen +3
Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing…