
prompt_injection
Benchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…

Benchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…

Adversarial image perturbation tool that uses SAM segmentation and CLIP models to evade AI-based scam image classifiers for security research.

Linux process identity cloaking tool that spoofs comm, argv, cmdline, environ, exe path, and VMAs via an 11-phase prctl pipeline to impersonate…

Experiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…

Fully automatic censorship removal for language models

Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…
