RLCDAlignBench
sumleo/rlcdalignbenchBenchmark suite and code for detecting AI alignment failures, with 44 benchmarks across ten failure types and a zero-shot RLCD detector evaluated on…
ai-securityanomaly-detectioncurated-resources+4
1
sumleo/rlcdalignbenchBenchmark suite and code for detecting AI alignment failures, with 44 benchmarks across ten failure types and a zero-shot RLCD detector evaluated on…
selectstar-ai/finred-paperfinance domain specific red-teaming benchmark evaluation rubric
alex66366/odpureBlack-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…
norrrrrrr-lyn/wainjectbenchBenchmarking prompt injection detections for web agents.
zjuwyh/shadowmemDefensive framework that maintains a safety-focused shadow memory to detect and block prompt-injection and long-horizon threats against LLM agents…
resharma/ajarMeasuring Open Privilege in Agent Defenses
usama1002/deleting-the-traceExperiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents
bardlaudian/cve-2024-37054Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.
clearlotus-git/cve-2024-37054-pocProof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…
safety-research/red-teaming-auto-modeResearch code for red-teaming AI auto-mode monitors, including simulation evals, fuzzing, and monitor implementations for Claude Code and Codex…
openai/privacy-filterBidirectional token-classification model for PII detection and masking in text, with CLI for redaction, evaluation, and finetuning on-premises.
ml-security-research-lab/cachetrapResearch code for a gray-box trojan attack that flips a single KV-cache bit in fine-tuned LLM classifiers and measures per-class attack success rate.
binzhwang/actguardPre-execution action-auditing defense that detects and masks indirect prompt injection in tool-using LLM agents using embedding retrieval and…
off-by-1-labs/flawedFix-Like Artifacts With Embedded Defects
xiaoyan-lisa/defenses-for-tool-integrated-llmResearch code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…
zhou-cybersecurity-ai/synghostSyntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models
siyuanli00/intactResearch code reproducing multi-turn LLM jailbreak experiments (FITD, MRCJ, ActorAttack, X-Teaming) from the SoK intent-oriented systematization…
zdcslab/rubrics-as-an-attack-surfaceResearch code for Rubric-Induced Preference Drift (RIPD): evolutionary rubric search, benchmark-preserving selection, and DPO policy misalignment…