Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones, so Active Attention Probing is introduced, which supplies a fixed content independent measurement coordinate.
Abstract
Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones. That separation is then read as evidence that the score will also catch the attacks that succeed. Harmful intent is a property of the prompt. Jailbreak success is an outcome produced later by a particular target model, decoding policy, and judge. A filter tuned on a score that measures the wrong quantity spends its false positive budget on attacks that would have failed anyway. In this paper we audit that inference. Attention based measurements are usually read from prompt dependent locations, so a wrapper changes both the content being judged and the place the signal is taken from. We therefore introduce Active Attention Probing, which supplies a fixed content independent measurement coordinate. We pair every base goal with a plain and a wrapped version and generate real completions from the target models. On Llama, wrapping raises harmful generation from 0.05 to 0.27 while harmful intent AUROC falls from 0.936 to 0.803, so the attacks grow more dangerous while the prompts look safer to the score. Among wrapped harmful prompts the outcome AUROC is 0.220, which places the attacks that succeeded below the attacks that failed. Rare token, passive, and detector derived channels reproduce the reversal on the same matched design, and the reversal itself persists across three target models, seven attack families, and two independent judges. Distribution shift then degrades calibration and threshold transfer before it degrades ranking.
Automatic safety judges -- for example Llama Guard, or GPT-4o given a grading prompt -- produce the numbers behind reported jailbreak success rates, defense evaluations, and safety leaderboards. We ask whether these judges grade what a reply contains or how it sounds. We place a fixed piece of text before or after a mo...
Yong-Xin Zhou, Wen-Bo Ye, Yuan-Zhe Liu et al.· 0 citations
This paper does an audit of defense mechanisms under jailbreak attacks on locally deployed models by tracing each failure back to the specific assumption it relies on.
As automated fact-checking scales on social media, large language model (LLM) verdict scores can look stronger than warranted. One reason is that evaluations mix in information that was not knowable at claim time. Two channels are easy to conflate: outcomes memorized in pre-training and retrieved evidence published aft...
The first controlled adversarial evaluation of Jev is presented, which suggests that Jev resists attacks on tasks with a clear rule to check but is more exposed on tasks that call for an overall judgment.
A confidence-interval (CI) filtered two-stage judge-screening framework that reduces the rate of selecting judges that fail the unsafe-recall screen by an order of magnitude and emits an explicit low-confidence or abort verdict when no judge has sufficient calibration evidence.
Ji-Xiang Yang, Jun-Fei Yi, Jin-Han Li et al.· IEEE Access· 0 citations
Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code. Prior work shows third-party marketplaces host malicious skills that give attackers direct influence over the victim's agent. The emerging defense scans skill...