{"data":{"id":"6736fe18-0296-488c-acba-9d5423038335","title":"TRAP: Tree-Guided Reinforcement-Augmented Probing for Automated LLM Jailbreaking","summary":"TRAP is a black-box framework for automated jailbreak strategy discovery against aligned LLMs. It organizes known jailbreak methods and successful attack templates into a semantic strategy tree, and a tree-structured gradient bandit reinforcement-learning policy uses evaluator feedback to pick and update strategies across attack objectives. On AdvBench across seven aligned LLMs, TRAP outperforms its counterparts on six models under the reported settings, with attack success rates of 45.6% to 97.9%.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.17313v1","publishedAt":"2026-10-12T19:10:37.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"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":"2026-10-12T19:10:37.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.97,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}