» Tag
attacks
5 postsAn Open Agent Security Benchmark: Uncaught Attacks
An open benchmark featuring 497 attacks targeting modern LLM agents has been established.
New hardware exposes encrypted memory to RAM attacks
A new hardware interposer exposes encrypted memory to RAM attacks, raising significant security concerns for cloud services.
Measuring Malicious Intermediary Attacks on the LLM Supply Chain
A systematic study examining malicious intermediary attacks on LLM supply chains is presented.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comSparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems
SparSEEty addresses token extraction attacks on LLM serving systems, achieving high reconstruction accuracy with minimal overhead.
MemGhost: Attacker Model Plants Persistent False Memories via Email
MemGhost successfully injects persistent false memories into OpenClaw and Claude Code SDK agents using just one email.