{"data":{"id":"1e2d9ff3-7994-4db2-9d2f-f39825447382","title":"Toward Polymorphic Backdoor Against Semantic Communication via Intensity-Based Poisoning","summary":"Researchers created SemBugger, a polymorphic backdoor attack (a type of hidden malicious code that can change its behavior) against semantic communication (SC, a system where AI learns shared knowledge to compress and transmit information efficiently). The attack uses variable-intensity triggers to poison training data and manipulate the system into producing different malicious outputs while appearing normal, but the researchers also developed a defense mechanism using controlled noise that can resist these attacks.","solution":"The source proposes a provable robustness defense that resists SemBugger attacks through a controlled noise mechanism, which operates by strategically adding noise to semantic communication inputs, with theoretical lower bounds on defense effectiveness provided. Experiments show this designed defense effectively neutralizes SemBugger attacks.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11501285","publishedAt":"2026-04-30T13:18:58.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_poisoning"],"issueType":"research","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-04-30T13:18:58.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"training_data","llmSpecific":false,"classifierConfidence":0.85,"researchCategory":"peer_reviewed","atlasIds":null}}