From the 1 of 13 linked papers with an AI index.
13 papers
When Binaries Talk Back: Representation-Confusion Attacks on LLM-Assisted Reverse Engineering
Igor Santos-Grueiro
The paper studies how malicious binaries can trick large language model (LLM)‑based reverse‑engineering tools into treating crafted data as authoritative instructions, introducing…
Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents
Igor Santos-Grueiro
LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result.…
Context-to-Execution Integrity for LLM Agents
Igor Santos-Grueiro
Language-model agents read attacker-writable context to solve tasks. Tool execution needs a separate authority check for protected sink fields, sink-interpreted payloads, and the i…
Ghost in the Context: Policy-Carriage Integrity in LLM Agents
Igor Santos-Grueiro
LLM agents choose actions from bounded decision states assembled from system policy, runtime state, tools, workload content, and the final request. We study policy-carriage integri…
On Good Authority: Release-Authority Measurement for Registry-Mediated Package Ecosystems
Igor Santos-Grueiro
Dependency graphs reveal where released code can flow; release-authority records reveal how a release reached users. A package can keep the same downstream exposure while its publi…
What Browsers Do in the Shaders: A Measurement Study of WebGPU Privacy
Igor Santos-Grueiro
WebGPU lets ordinary web pages run GPU workloads through a validated programming model. Validation protects memory safety, but shared browser, driver, OS, and GPU state can still e…