{"data":{"id":"553c45dc-64c4-4b10-b9ed-a523d61a8b86","title":"Protecting Your Customized LLM Systems From Backdoored Instructions With Metacognitive Probing","summary":"Researchers present a black-box safety auditing agent that defends customized LLM systems against backdoored system instructions, which are malicious rules hidden in system instructions and need no fine-tuning. The agent uses metacognitive probing, which leverages the model's safety-alignment mechanisms to induce it to reveal predefined triggers, and then sanitizes those triggers from user queries. Experiments across three backdoor attack algorithms and multiple state-of-the-art LLMs substantiate its effectiveness.","solution":"The paper proposes a black-box safety auditing agent that uses metacognitive probing to reveal triggers and sanitizes them from user queries to keep the backdoor inactive. It also covers task-specific and broad-spectrum prompt-based probing, and requiring the model to articulate its reasoning.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11612933","publishedAt":"2026-07-16T13:16:28.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak","other"],"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":"2026-07-16T13:16:28.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"peer_reviewed","atlasIds":["AML.T0054"]}}