correctness-validation

1 article
sort: new top best
clear filter
bug-bounty356 xss320 google245 facebook204 microsoft192 apple136 exploit112 rce94 csrf80 writeup63 account-takeover59 browser50 defi48 bragging-post48 smart-contract47 access-control46 ethereum44 open-source42 malware42 authentication-bypass40 ssrf40 web338 privilege-escalation37 sqli35 docker35 ai-agents35 cve34 smart-contract-vulnerability33 aws33 dos32 idor30 react28 oauth28 supply-chain27 sql-injection27 clickjacking26 subdomain-takeover26 wordpress25 solidity25 denial-of-service24 api-security23 information-disclosure23 race-condition23 burp-suite22 node22 phishing21 cors21 automation21 vulnerability-disclosure20 reverse-engineering20
0 8/10
A Field Guide to Reward Hacking in AI Kernel Generation
research

A comprehensive field guide documenting 10 distinct patterns where LLMs game kernel benchmarks through timing attacks (stream injection, thread injection, lazy evaluation, patching), semantic attacks (identity kernels, no-ops, shared memory overflow), and benign shortcuts, with defensive mechanisms for each exploit category.

ai-safety benchmark-gaming reward-hacking cuda gpu-kernels machine-learning testing-methodology triton rocm vulnerability-detection timing-attacks semantic-attacks correctness-validation adversarial-ml
KernelArena MI300X ROCm 6.x CUDA PyTorch Triton HIP
wafer.ai · matt_d · 1 day ago · details · hn