{"data":{"id":"17576976-18b1-4a97-9bcb-d99b93f33fa8","title":"Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language Models","summary":"This empirical study tests five adversarial jailbreaking attack families against seven LLMs, including Llama-3-8B, Mistral-7B, Qwen2.5-7B and Gemma2-9B, and four defenses. Obfuscation attacks reach a mean attack success rate of 54.3% and bypass every evaluated model with nonzero success. Model size does not predict robustness (Spearman r=-0.57, p=0.18), and self-reminder prompting cuts ASR from 44% to 10% on Mistral-7B and from 48% to 5% on Llama-3.1-8B with no reported false positives.","solution":"Self-reminder prompting is the most consistent defense in the evaluation, reducing ASR from 44% to 10% on Mistral-7B and from 48% to 5% on Llama-3.1-8B, with zero false positives and no additional inference cost.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.39509v1","publishedAt":"2026-10-29T07:07:58.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Meta","Mistral","Google","Microsoft"],"affectedVendorsRaw":["Llama-3-8B","Llama-3.1-8B","Llama-3.2-3B","Mistral-7B","Qwen2.5-7B","Gemma2-9B","Phi-4-14B"],"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":"2026-10-29T07:07:58.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety","integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}