NY1024/AgentSafety-Papers
Daily Tracking of LLM Agent Security Papers on arXiv
Research interest is on Trustwothy AI.
Repositories
NY1024/ny1024.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
NY1024/pikit
A composable toolbox of classic prompt-injection attacks, defenses, and indirect-injection channels .
NY1024/RACE
NY1024/ClawGuard
ClawGuard is a comprehensive security toolkit designed to mitigate risks associated with autonomous agents, such as OpenClaw and other LLM Agents.
NY1024/Foundation-Model-Paper-Notes
NY1024/BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt
NY1024/Jailbreak_GPT4o
NY1024/PRISM-Programmatic-Reasoning-with-Image-Sequence-Manipulation-for-LVLM-Jailbreaking
official code
NY1024/Evolving-Deception
Evolving Deception: When Agents Evolve, Deception Wins
NY1024/AIG-Recipes
AI-Infra-Guard Recipes: Scripts, data, and charts for academic research and method extraction
NY1024/SecAI_Radar
SecAI Radar: Automated tracking of AI security papers from CCF-A conferences (S&P, CCS, USENIX Security, NDSS, NeurIPS, ICML, ICLR, CVPR, ECCV, EMNLP, ACL, AAAI, SaTML)
NY1024/Proactive-ai-sentinel-guard
办公场景的主动式 AI 安全守门人：可交互原型，支持规则模拟与 LLM 风险预判、解释与触达策略。
NY1024/pixel-mecha-battle
A retro pixel-art 2-player mecha battle game built with pure HTML/CSS/JS. Zero dependencies.
NY1024/AI-Infra-Guard
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
NY1024/AegisLink
灵盾 — AI Agent 身份与权限中枢
NY1024/SafeBench
NY1024/VEIL
Code and data for paper VEIL: Jailbreaking Text-to-Video Models via Visual Exploitation from Implicit Language
NY1024/Awesome-Trustworthy-GenAI
NY1024/DeepSeek-Safety-Eval
NY1024/Best_Practice_in_AI_for_Security
Best_Practice_in_AI_for_Security
NY1024/Awesome-Datasets-for-Cybersecurity
NY1024/ATLAS_Challenge_2025
NY1024/TRIP
NY1024/SafetyEval_LRM
NY1024/personal-backup
backup
NY1024/MJBench
NY1024/Eval_GPT4o_on_SelectiveTest
Eval Performance of GPT-4o on Selective High School Placement Test
NY1024/GPTSecurity
塑造未来的安全领域智能革命
NY1024/Open-Source-Backdoor-Learning
official/unofficial open source code/dataset for backdoor attack and defense