{"data":{"id":"b9524181-77be-4b3a-9853-4a7377d4259e","title":"AI models more vulnerable than claimed when faced with iterative attacks","summary":"A Cisco study found that popular AI models from OpenAI, Anthropic, Google, and others are much more vulnerable to attack when faced with multiple prompts in a conversation compared to single-prompt tests. Current safety benchmarks (standardized tests that measure how well models resist harmful requests) only test models with one prompt at a time, but real attackers use iterative techniques like role-playing, breaking tasks into smaller steps, and gradually escalating requests across multiple turns, which bypass safety guardrails far more effectively than official scores suggest.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://www.csoonline.com/article/4177903/ai-models-more-vulnerable-than-claimed-when-faced-with-iterative-attacks.html","publishedAt":"2026-05-27T21:48:19.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI","Anthropic","Google","Meta","Microsoft","Amazon","Mistral"],"affectedVendorsRaw":["OpenAI","Anthropic","Google","xAI","Amazon","Meta","Mistral","Alibaba","DeepSeek","Zhipu","Microsoft","Claude Opus","GPT-5.4","Gemini 3 Pro","Grok 4.1","Nova Lite","Nova Lite 2","Nova Micro"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-05-27T21:48:19.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}