AESOP enables path-aware adversarial attacks that inflate FLOPs in ML pipelines by up to 2407x, 20x more than single-model baselines, even under defenses that force throughput collapse or data loss.
Loki: A system for serving ml inference pipelines with hardware and accuracy scaling
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
LEO performs cross-vendor backward slicing from stalled GPU instructions to attribute root causes to source code, enabling optimizations that produce geometric-mean speedups of 1.73-1.82x on 21 workloads.
Empirical study of agentic LLM generation of parallel Julia code finds reliable execution only at small scales with recurring failures in task dependencies and scheduling at larger scales.
KEET uses LLM agents to generate data-grounded natural language explanations of performance issues in GPU kernels from Nsight Compute profiles and shows these improve downstream LLM-based optimization tasks.
citing papers explorer
-
AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines
AESOP enables path-aware adversarial attacks that inflate FLOPs in ML pipelines by up to 2407x, 20x more than single-model baselines, even under defenses that force throughput collapse or data loss.