{"data":{"id":"3e0ebb97-7464-4494-b1a2-74a3438d1a6e","title":"The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents","summary":"Researchers propose an adversarial self-evolution framework that exposes vulnerabilities in LLM-based search agents, which are susceptible to malicious information injection and stealthy context manipulation. The framework uses bi-level optimization between attacker strategy evolution and defender adaptive mitigation, driven by Contrastive Rollout Evolutionary Optimization (CREO) in a controlled sandbox. Experiments on multi-hop QA benchmarks and frontier LLMs show higher attack efficacy than static baselines, which the authors say underscores the need for more robust defenses.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.03754v1","publishedAt":"2026-11-02T11:06:25.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["LLM-based search agents","frontier LLMs"],"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":"2026-11-02T11:06:25.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","confidentiality"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}