Introduces MOOD benchmark for OOD LLM alignment failures and shows guard models plus Mahalanobis and perplexity OOD detectors improve recall from 39% to 45% with positive scaling.
month = nov, year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3roles
background 2polarities
background 2representative citing papers
The paper releases a 1,554-prompt consensus-labeled bank separating executable malicious code requests from security knowledge requests, validated by five-model majority labeling with Fleiss' kappa of 0.876.
A malicious BYOK relay can rewrite an LLM agent's execution-bearing response fields after safety alignment, achieving 73.5-99.1% attack success on agent benchmarks while bypassing model defenses.
citing papers explorer
-
Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
Introduces MOOD benchmark for OOD LLM alignment failures and shows guard models plus Mahalanobis and perplexity OOD detectors improve recall from 39% to 45% with positive scaling.
-
A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts
The paper releases a 1,554-prompt consensus-labeled bank separating executable malicious code requests from security knowledge requests, validated by five-model majority labeling with Fleiss' kappa of 0.876.
-
Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM Agents
A malicious BYOK relay can rewrite an LLM agent's execution-bearing response fields after safety alignment, achieving 73.5-99.1% attack success on agent benchmarks while bypassing model defenses.