{"data":{"id":"dfb43970-2e7f-44ef-82ef-3ff8d8703809","title":"Amplifying Latency and Cost of LLM Inference via Rowhammer Attack","summary":"Researchers present LLVMhammer, a Rowhammer attack that induces a bit-flip in Triton's compilation pipeline so that it generates a functionally identical but suboptimal GPU kernel. Because Triton caches the kernel on disk, one successful bit-flip causes persistent slowdown across later inference runs. Tested on Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and Deepseek-llm-7B-chat on NVIDIA RTX 4090 and AMD RX 7900 XTX GPUs, the attack raised inference latency by 4-16% and could reduce BERTScore to as low as 25%.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.30798v1","publishedAt":"2026-10-22T06:24:35.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["NVIDIA","Meta","Mistral"],"affectedVendorsRaw":["Triton","Qwen2.5-7B-Instruct","Llama-3.1-8B-Instruct","Mistral-7B-Instruct-v0.3","Deepseek-llm-7B-chat","NVIDIA RTX 4090","AMD RX 7900 XTX"],"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":"2026-10-22T06:24:35.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["availability","integrity"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}