heretic
p-e-w/hereticTraining-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
adversarial-attackai-securityeducation+3
p-e-w/hereticTraining-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
huhusmang/awesome-llms-for-vulnerability-detectionThe community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers…
online-ml/riverStreaming machine learning library for incremental learning on data streams, providing online estimators, drift and anomaly detection, pipelines,…
joshuaprovoste/deserializerAST-based Static Code Analyzer with Agentic LLM-Powered Relationship Mapping to discover Python RCE paths and deep deserialization chains on AI, LLM,…
unit8co/dartsA python library for user-friendly forecasting and anomaly detection on time series.
jev-sec/jev-idsBlazing-Fast Token-Efficient Intrusion Detection System (IDS) based on TypeSafe's Jev.
cbuijs/sdproxyDNS Proxy that is simple and fast with not so simple features. Focused on routed DNS forwarding, filtering and parental control.
lzwhehe/benign-instruction-benchRe-evaluating prompt-injection detectors on LLM agent tool outputs (paper draft, scripts, scores)
seclog-open/seclogCollects multi-source security logs from reproducible Docker attack scenarios, builds attack chains, and provides the SecLog-Bench-216 benchmark for…
francescopace/espectreESPectre - Motion detection system based on Wi-Fi spectre analysis (CSI), with Home Assistant integration.
0x0allenace/soc-analyst-portfolioA curated portfolio showcasing my SOC investigations, threat hunting projects, DFIR labs, detection engineering, technical blogs, and cybersecurity…
suels-group/beyond_asrResearch code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…
syscallx-18113/apkx-hunterC-based Android static analysis framework for decompilation, secret detection, endpoint discovery, permission analysis, and native library scanning…
phkhanhtrinh23/agasLLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…
moontea0416/webmirageAdversarial image attacks on vision-language web agents, from visual grounding to browser execution
stardust457/sldrDefense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…
iqsec-lab/freemocaMemory-free continual learning framework for malware classification using mode connectivity-based interpolation. Supports class-incremental and…