CuraSec

tag: Speculative-Decoding · 1 items

Learn archived ADSD Attack Collapses Speculative Decoding Acceptance, Slows LLM Inference 62%
2026-07-27 · arXiv cs.CR · source ↗ #adversarial-ml#llm-security#speculative-decoding
  • Engineer — Learn: Novel prompt-suffix attack degrades speculative decoding throughput without corrupting outputs, affecting any deployment using draft-target inference acceleration (vLLM, TGI, etc.). No patch or mitigation exists yet; file this when designing LLM serving infrastructure to justify input validation and rate controls at the prompt layer.
  • SOC/IR — Skip
  • Leader — Skip