{"data":{"id":"5d043057-9c30-4497-89aa-31fd4c973107","title":"RL-ATTACK: A Generalized Black-Box Adversarial Attack on Language Models via Reinforcement Learning","summary":"The paper presents RL-ATTACK, a trainable black-box framework that uses reinforcement learning to generate adversarial transformations against language models without gradient access. On natural language inference, it reduces post-attack accuracy to 2% within 20 queries, and against generative models it beats an optimization-based baseline in 4 of 6 settings. The authors report that no reward design or training setting is consistently dominant.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.08711v1","publishedAt":"2026-11-05T21:06:21.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-05T21:06:21.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}