1649 matches found
Defenses-for-Tool-Integrated-LLM
ããŒã«çµ±ååLLMãšãŒãžã§ã³ãã«å¯Ÿããæµå¯Ÿçæ»æãžã®æ±çšé²åŸ¡ ãã®ãªããžããªã«ã¯ãããŒã«çµ±ååå€§èŠæš¡èšèªã¢ãã«ïŒLLMïŒãšãŒãžã§ã³ããæµå¯Ÿçæ»æããé²åŸ¡ããããã®ç§ãã¡ã®ãããžã§ã¯ãã®ã³ãŒããšå®éšãå«ãŸããŠããŸãã æŠèŠ ç§ãã¡ã¯Agent Security BenchïŒASBïŒãåºç€ãšããŠãããŒã«ãšæ§é åæšè«ïŒäŸïŒchain-of-thoughtãreflectionïŒã®çµ±åããè€æ°ã®ã¿ã¹ã¯ã·ããªãªã«ãããæµå¯Ÿçããã³ããã«å¯ŸããLLMãšãŒãžã§ã³ãã®è匱æ§ã«ã©ã®ããã«åœ±é¿ããããè©äŸ¡ããŸãã ãã®ãªããžããªã«ã¯ä»¥äžãå«ãŸããŸãïŒ...
Scrapegraph-ai v2.3.1
ð Looking for an even faster and simpler way to scrape at scale only 5 lines of code? Check out our enhanced version at ScrapeGraphAI.com! ð ð·ïž ScrapeGraphAI: You Only Scrape Once English | äžæ | æ¥æ¬èª | íêµìŽ | Ð ÑÑÑкОй | TÃŒrkçe | Deutsch | Español | français | Português | Italiano ScrapeGraphAI is a...
o3_finds_cve-2025-37899
ã«åºã¥ã Linuxã«ãŒãã«ã®SMBå®è£ ã«ããããªã¢ãŒããŒããã€è匱æ§CVE-2025-37899ão3ã䜿ã£ãŠçºèŠããæ¹æ³ ã¿ãŒã²ããèåŒ±æ§ ollama èåŒ±æ§ CVE-2024-37032 https://github.com/ollama/ollama/releases/tag/v0.1.34 https://github.com/ollama/ollama/compare/v0.1.33...v0.1.34 ã³ããã: 2a21363 以äžã®ããã« llm CLI ã䜿çšãã pip install llm llm keys set openai llm --sf...
Xalgorix Autonomous AI Pentesting Agent 4.6.153
Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...
T-MAP
T-MAP: è»è·¡èªèé²åæ¢çŽ¢ã«ããLLMãšãŒãžã§ã³ãã®ã¬ããããŒãã³ã° T-MAP ã¯ãMCPãµãŒããŒäžã®LLMãšãŒãžã§ã³ããã¬ããããŒãã³ã°ããããã®è»è·¡èªèåé²åæ¢çŽ¢ãã¬ãŒã ã¯ãŒã¯ã§ããå®è¡è»è·¡ã«åºã¥ããŠæµå¯Ÿçããã³ãããå埩çã«çæã»å€ç°ããã倿§ãªãªã¹ã¯ã«ããŽãªã𿻿ã¹ã¿ã€ã«ã«ããã£ãŠãšãŒãžã§ã³ãã®è匱æ§é åããããã³ã°ããŸãã ð§ ã»ããã¢ãã pip install -r requirements.txt èŠä»¶: Python 3.11以äžãæ»æè ã¢ãã«ãšã¿ãŒã²ããã¢ãã«çšã®APIããŒã1ã€ä»¥äžã®MCPãµãŒããŒãžã®ã¢ã¯ã»ã¹ã ð ã¯ã€ãã¯ã¹ã¿ãŒã åäžãµãŒã㌠python...
linux-kernel-codex-harness
Kernel Codex Harness íêµìŽ | English ç ç©¶ããŒã« · ååã€ã³ããŒã: 2026幎4æ3æ¥ Â· ããã¥ã¡ã³ãæ¹èš: 2026幎7æ11æ¥ äžæ žå²åŠ â å€éšã·ã°ãã« ã¢ãã«æšè«ã®å€éšã§èšç®ãããåçŸå¯èœãªèŠ³æž¬å€ã«æ³šæãåããããåªå 床ã蚌æãšèª€è§£ããŠã¯ãªããªãã ãããžã§ã¯ãã®ç¶æ ã...
llm-council-vapt
LLM Council â VAPT ì·šìœì ë°ê²¬ ê²ìŠ íŽëŒìŽìžížìê² ì ë¬ëêž° ì ì ì¹ší¬ í ì€íž 결곌췚ìœì ë°ê²¬ë¥Œ ê²ìŠíë ëžëŒìžë íŒìŽ ëŠ¬ë·° íìŽíëŒìžì ëë€. ë 늜ì ìž ì ë¬žê° êŽì ë ìŠìŽ ê²°ê³Œë¥Œ íê°íê³ , ìë¡ ëžëŒìžë 늬뷰륌 ìííë©°, ìì¥ChairmanìŽ íëì ê²ìŠë íê²°ì ì¢ í©í©ëë€. ë³Žê³ í ê°ì¹ê° ìëì§, ì¬ê°ëê° ì ì í ì¡°ì ëìëì§ ì¬ë¶ë¥Œ íëší©ëë€. ë ê°ì§ ì€í ë°©ì: 몚ë| ìì¹| ì€ëª ---|---|--- ìë ìì¥ Manual Chairman| claude.ai / Claude ì± ì±í | ê° ë ìŠë¥Œ ê°ë³ì ìŒë¡...
IPI-exposure-signal
IPIé²åºã·ã°ãã« ããã¯ãç§ãã¡ã®è«æãYour Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposureãã®ã³ãŒããªããžããªã§ãã ArXivçãšè«æãªã³ã¯: https://arxiv.org/abs/2608.02657 ãã®ãªããžããªã¯ãæœåšçãªIPIé²åºã·ã°ãã«ã®ãããŒãã³ã°ãã€ãã©ã€ã³ïŒAgentDojoãã¬ãŒã¹åéãIPIãªã¹ã¯ã©ããªã³ã°ãé ãç¶æ ã®ãã£ãŒãã£ãŒåãIPIé²åºãããŒãã®ãã¬ãŒãã³ã°/è©äŸ¡ïŒãå®è£ ããŠããŸãã åŒçš...
gemini-2.5-pro-nf-tables-red-teaming
Gemini 2.5 Pro nftables ã¬ããããŒãã³ã°äºäŸç ç©¶ CVE-2023-32233 LLMå®å šæ§ç ç©¶ | 責任ããé瀺 | AIã¢ã©ã€ã¡ã³ãè©äŸ¡ ç ç©¶è : Niranj R Mahaswar Destawell Google AIè匱æ§å ±å¥šéããã°ã©ã : 889286 â å¯Ÿè±¡å€ æŠèŠ ãã®ãªããžããªã¯ãLinuxã«ãŒãã«ã®èåŒ±æ§ CVE-2023-32233 ïŒnftables ã¬ãŒã¹ã³ã³ãã£ã·ã§ã³ / Use-After-FreeïŒã«é¢ããæè¡çããªããã£ãã«ã€ããŠãããã³ãã£ã¢ã¢ãã«ã察象ã«è¡ã£ãæ¯èŒ LLMã¬ããããŒãã³ã° å®éšãèšé²ãããã®ã§ãã...
promptfoo v0.124.0
Promptfoo: LLM evals & red teaming promptfoo is a CLI and library for evaluating and red-teaming LLM-based apps. Stop using trial-and-error... start shipping secure, reliable agents Website · Getting Started · Red Teaming · Documentation · Discord Promptfoo is now part of OpenAI. Promptfoo remain...
Rubrics-as-an-Attack-Surface
æ»æå¯Ÿè±¡ãšããŠã®ã«ãŒããªãã¯: LLM審æ»å¡ã«ãããã¹ãã«ã¹ãªéžå¥œããªãã ð ããŒã¿ã»ãã ⢠ð€ åŠç¿æžã¿ã¢ã㫠⢠ð è«æ ⢠ð» ãªããžã㪠ãã®ãªããžããªã«ã¯ãRuomeng DingãYifei PangãHe SunãYizhong WangãSteven WuãZhun Dengã«ããè«ææ»æå¯Ÿè±¡ãšããŠã®ã«ãŒããªãã¯: LLM審æ»å¡ã«ãããã¹ãã«ã¹ãªéžå¥œããªããã®ã³ãŒããå«ãŸããŠããŸãã...
INTACT
SoK ãã«ãã¿ãŒã³ã»ãžã§ã€ã«ãã¬ã€ã¯å®éš ãã®ãªããžããªã«ã¯ãSoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks ã«ãããã¡ã«ããºã åæã«äœ¿çšãããã³ãŒãã®ãªãªãŒã¹çãå«ãŸããŠããŸãã ãªããžããªã¯ãè«æã®ä»é²Aã§èª¬æãããŠããå®éšã«å¿ èŠãªã³ãŒããããã³ãããèšå®ãã¡ã€ã«ãããŒã¿ã»ããã®ã¿ãä¿æããããã«æŽçãããŠããŸããçæããããã°ããã£ãã·ã¥ãã¡ã€ã«ãä»®æ³ç°å¢ã以åã®çµæãå³ãããã³ã¢ãããã¯ãªåæåºåã¯æå³çã«åé€ãããŠããŸãã å®éšã®å¯Ÿå¿è¡š è«æã®åã| ææ³| ã«ããŽãª| ããŒã«ã«ãã£ã¬ã¯ããª|...
benign-instruction-bench
ãã¬ãŒãã³ã°ãããã¹ãã«åæ Œããããš LLMãšãŒãžã§ã³ããå®éã«ããã³ããã€ã³ãžã§ã¯ã·ã§ã³æ€åºåšã䜿çšããå Žé¢ãããªãã¡ãšãŒãžã§ã³ããèªã¿åãããŒã«åºåã«ãããŠãããããåè©äŸ¡ããã ããŒã ã¯ãã³ãããŒã¯ã¹ã³ã¢ã«åºã¥ããŠã€ã³ãžã§ã¯ã·ã§ã³æ€åºåšãéžå®ãããæã ã¯ãããã®ã¹ã³ã¢ããšãŒãžã§ã³ãå éšã§ã®æåãäºæž¬ãããã©ãããæ€èšŒããã¹ã³ã¢ã®å€§åã¯ãã³ãããŒã¯ãæ€åºåšã®ãã¬ãŒãã³ã°ããŒã¿ã«ã©ãã ãè¿ãããæž¬å®ããŠããã«ãããªãããšãæããã«ããã ç¥èŠ 15ã®æ€åºåšïŒãªãŒãã³9ã€ãMetaã®Prompt Guard...
Xalgorix Autonomous AI Pentesting Agent 4.6.152
Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...
Newer and Bigger, but Safer? A Longitudinal Study of the Functionality-Security Gap in LLM-Generated Code
Large Language Models LLMs are widely used to generate code. Although their functional plausibility keeps improving, the generated code often contains security vulnerabilities. The functionality-security gap captures code that passes functional tests but fails security tests. A recent longitudina...
Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis
Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on prompt design. Existing research primarily compares prompting strategies using aggregate performance metrics, providing limited insight into why models fail or how...
HiTMS_steganography
HiTMS: é«ã¹ã«ãŒãããã»ãã«ãã¹ããªãŒã èšèªã¹ãã¬ãã°ã©ãã£ãã¬ãŒã ã¯ãŒã¯ LLMãã£ãã察話ã«ãããèšèªã¹ãã¬ãã°ã©ã㣠ã®ç ç©¶çšã³ãŒãã§ããåäžã¹ããªãŒã ã®ããŒã¹ã©ã€ã³ãšãè€æ°ã®ç¬ç«ããç§å¯ã¡ãã»ãŒãžãåæã«é ããGPUãããåŠçãæŽ»çšããŠã¯ããã«é«ãã¹ã«ãŒããããå®çŸãããããåãã«ãã¹ããªãŒã ïŒHiTMSïŒãããã³ã«ãå«ã¿ãŸãã Bob ã¢ãã«ã質åãã Alice...
xalgorix
Xalgorix â Open-source AI pentester that proves vulnerabilities Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported â so you get proof, not a pile of maybes to triage...
OpenHunterAI
OpenHunterAI ããªãã®ããŒã«ã«AIã¬ããããŒã ã ãŠã§ããAPIãLLMã¢ããªã±ãŒã·ã§ã³ã»ãã¥ãªãã£ã®ããã®æ»æè èŠç¹ã®æšè«ã ã¯ã€ãã¯ã¹ã¿ãŒã · ãšãŒãžã§ã³ãã¹ã㫠· è©äŸ¡ã¢ã㫠· ã¢ãŒããã¯ã㣠· ããã¥ã¡ã³ã · ã¹ã¿ãŒå±¥æŽ OpenHunterAIã¯ãã¹ã³ãŒããã¹ãã£ã³æŽ»åãæ€åºçµæãããã³ä¿®åŸ©ã1ã€ã® ããŒã«ã«ã¯ãŒã¯ã¹ããŒã¹ã«çµ±åããŸããã¢ã«ãŠã³ããªãã§éå§ããã¢ãã«ãããã€ããŒãæ¥ç¶ãã ææããŠããããŸãã¯ãã¹ããèš±å¯ãããŠããæ€èšŒæžã¿ã®å ¬éã¢ããªã±ãŒã·ã§ã³ ãè©äŸ¡ããŸãã æ©èœ| åŸããããã® ---|--- ããŒã«ã«ã¯ãŒã¯ã¹ããŒã¹|...
recipe-blog-encoding
recipe-blog-encoding !WARNING ìŽ íë¡ì ížë ì ì ìŒë¡ vibe-coding ìŒë¡ ìì±ëììŒë©° ìë§ë ìŽ ì ì¥ììì ë¶ë¶ì ìŒë¡ íì ëììµëë€, ìì±ìë ììŽëìŽê° ì¬ë¯žìë€ê³ ìê°í ë°ë³Žì ëë€. SEO ê²ì ë ìíŒ ì묞ì ì¬ì©íì¬ ë¹ë° ë©ìì§ë¥Œ ìžìœë©íë ë구ì ëë€ ì¬ì€ í롬íížë 묎ììŽë ë ì ììŒë©°, ê³µì í롬íížë ìžìœëì ëìœëê° ëìíë í€ìŒ ë¿ì ëë€. ì 겜 ìžìŽ ì€í ê°ë žê·žëíŒë¥Œ ì¬ì©íì¬ ìì°ì€ë¬ìŽ í ì€ížì ë¹ë° ë©ìì§ë¥Œ ìšê¹ëë€. ìë ë°©ì 1. ìžìœëë ë¹ë° ë©ìì§ì ê³µì í롬íížë¥Œ ë°ìµëë€...