AgentWatcher
wang-yanting/agentwatcherCausal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…
adversarial-attackai-securityeducation+2
9
wang-yanting/agentwatcherCausal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…
afterquery/vaderHuman-evaluated benchmark for assessing LLM performance on real-world vulnerability identification, explanation, and remediation across 15+ languages…
hannahxchen/llm-censorship-steeringCode for 'Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control'
mamadou-keita/deeclipImplementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"
andyshaw01/poisoncraftThis repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.
pppyb/secopdResearch implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…
jianshuod/ipi-exposure-signalResearch pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…
cognitive-functors/c4-meta-systemProduction AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…
q-rz/saffronInference scaling for LLM safety assurance
ryehr/rrc_steganographyProvably secure linguistic steganography embedding secret messages into LLM-generated text via rotation range-coding. Includes embed, extract, and…
jinxhy/awesome-moai-securityCurated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…
mouna23/ai-driven-mitre-attackThis repository demonstrates a machine learning pipeline for detecting MITRE ATT&CK techniques from logs and enriching the output using a local LLM.
nsol-nmsu/fml-networkFLNET2023 is a dataset designed for intrusion detection in Federated Learning scenarios. It's built using the CORE emulator, simulating a realistic…
benny-e/guarddML-Based behavioral endpoint detection system for Linux machines
yeasen-z/leakgaugeDetects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.
aniketkarne/aco-prompt-shieldStop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…
mdshoaibuddinchanda/zombieguardML-based detection of Zombie ZIP archive header evasion attacks (CVE-2026-0866)
sec5gloc/sec5glocAdversary-resilient deep learning architecture for secure 5G indoor localization, combining CNN and multi-head attention to defend against signal…