{"data":{"id":"d54e6ebc-163d-4062-94cc-0f260dbab9f9","title":"Gem5-Shark: Smaug-based Heterogeneous Deep Learning Accelerator Security and Robustness Evaluation and Characterization Framework","summary":"Gem5-Shark is a cycle-level simulation framework, built on Gem5-Aladdin's Smaug, for evaluating security threats to heterogeneous deep learning accelerators before deployment. It integrates eight threat vectors across dataset, compilation, SoC communication and accelerator execution stages, including two new compilation-stage attacks, Operator Attack (OPAtt) and Tiling Attack (TAtt). Across Minerva, LeNet-5, VGG-16 and pretrained LLMs up to 8B parameters, the attacks degrade accuracy by up to 97.7%, raise latency by up to 84× and implant backdoors with as few as 20 poisoned fine-tuning samples.","solution":"Two defenses are proposed: a compiler-stage tiling range check and a host-side finish-flag watchdog, each removing over 99% of the injected overhead on CNNs and LLMs.","labels":["security","research"],"sourceUrl":"https://doi.org/10.1145/3862333","publishedAt":"2026-11-07T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["data_extraction","supply_chain","jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Smaug","Gem5-Aladdin","Minerva","LeNet-5","VGG-16","LLMs up to 8B parameters"],"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":"2026-11-07T00:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","integrity","availability","safety"],"aiComponentTargeted":"framework","llmSpecific":false,"classifierConfidence":0.93,"researchCategory":"peer_reviewed","atlasIds":["AML.T0010","AML.T0054"]}}