BalCCon2k25·30 min
Ali Abdollahi
Industry experts analyze emerging threats surrounding Ali Abdollahi - Agent 47, LLM Based Adversary Framework for Real World OffSec Ops.
llmframeworkabdollahi+1
llm
168 talks tagged with this topic.
Filters+
Loading filters…
1–24 of 164 talks / 168 · loading…
Black Hat·37 min
Xiangfan Wu · Lingyun Ying · Guoqiang Chen · Yacong Gu · Haipeng Qu
Engineers explore architecture and security mechanisms for Cache Me, Catch You: Exploiting LLM Caching Layers in vLLM, GPTCache & Friends.
llmcachecatch+3
Black Hat·41 min
Shusei Tomonaga
Industry experts analyze emerging threats surrounding Graph-Aware LLM for Windows Logon with a Closed-Loop Guarded Detection Agent.
windowsllmdetection
Black Hat·25 min
Yinyi Wu · Yingqi Shi · Yuchong Xie · Cheng Li · Yizhuo Wang
Industry experts analyze emerging threats surrounding Large-Scale macOS PID-Domain Vulnerability Discovery with LLM Reasoning.
macosllmvulnerability-discovery
Black Hat·39 min
Engineers explore architecture and security mechanisms for Tinker Tailor LLM Spy: Investigate & Respond to Attacks on GenAI Chatbots.
llmtinkertailor+3
Black Hat Europe 2025·39 min
Andrew Konstantinov · Irina Iarlykanova
Industry experts analyze emerging threats surrounding Stress-Testing SAST And LLMs On Modern Web Backends.
websaststress-testing+3
Black Hat Europe 2025·28 min
Pengyu Ding · Ziteng Xu · Zhiniang Peng · Dongliang Mu
Analysts investigate attack surfaces and defenses concerning Token Injection: Crashing LLM Inference With Special Tokens.
llminjectiontoken+3
BlueHat India 2025·29 min
Security researchers examine technical aspects of Unleashing LLMs: Mastering the Art of Guardrail Evasion.
evasionllmmastering+1
Briefings·37 min
Tien-Chih Lin · Wei Chieh Chao · Zhao-Min Chen
IDA Pro feat. MCP (Model Context Protocol) is truly amazing.
reverse-engineeringmalware-analysisctf+3
Briefings·41 min
Estelle Ruellan · Olivier Bilodeau
Threat analysts uncover operational security blunders and digital breadcrumbs left by state-sponsored threat actors during cyber heists.
social-engineeringthreat-intelligenceai+3
Briefings·30 min
Zong Cao · Zhengzi Xu · Yeqi Fu · Yuqiang Sun · Kaixuan Li · Yang Liu
Imagine the process of a human security auditor.
llmdetectionmedical+3
Briefings·24 min
Qinrun Dai · Yifei Xie
Vulnerability discovery traditionally relies on two primary approaches: manual auditing and fuzzing.
vulnerability-researchautomationllm+3
Briefings·26 min
Jiashuo Liang · Guancheng Li
Introduces a novel gradient-based prompt-injection technique that can generate universal triggers to manipulate open-source Large Language Model (LLM) outputs.
open-sourceaillm+3
BSides Lisbon·42 min
Tiago Henriques (Balgan)
Tiago Henriques (Balgan) investigates [BSL2023] The Hype and Reality of Using LLMs for Cybersecurity.
bsl2023hypereality+1
BSides Lisbon 2025·32 min
Davide Cioccia
Davide Cioccia explores [BSL2025] Backdooring LLM and bypassing HuggingFace malware scanners.
llmbsl2025backdooring+3
BSides TLV·29 min
Inga Cherny
Inga Cherny examines LLMs Suck at Cyber Intel—Unless You Hack Them Right.
llmsuckintel+3
BSidesSF 2025·19 min
Matthew Sullivan · Dominic Zanardi
Engineers explore architecture and security mechanisms for Everyday AI: Leveraging LLMs for Simple...( Matthew Sullivan, Dominic Zanardi).
everydayleveragingllm+2
CONFidence 2025·37 min
Kai Iyer
Presenters detail vulnerability discovery and exploitation in Kai Iyer - Local LLMs in Action: Automating CTI to Connect the Dots.
ctilocaliyer+3
CornCon·32 min
Shadow AI
Engineers explore architecture and security mechanisms for CC9.T3F.Aaron Turner - Shadow AI - how un-controlled LLMs are impacting enterprises.
aaronturnershadow+3
Creator Stage·52 min
Dane Sherrets · Shlomie Liberow
Deep dives into adversarial prompt injection, context poisoning, and RAG manipulation flaws to help researchers find and demonstrate high-impact AI vulnerabilities.
ai-securityprompt-injectionbug-bounty+2
Crypto and Privacy Village·48 min
Patrick Walsh
Demonstrates model inversion and embedding inversion attacks against LLMs and RAG systems, showing how sensitive personal data can be extracted from vector databases.
ai-securityprivacyllm+2
CypherCon 8.0·53 min
Wolfgang Goerlich | CypherCon 8.0
Wolfgang Goerlich | CypherCon 8.0 investigates Surviving the Robot Apocalypse 2: Dawn of the Rise of the LLMs.
survivingrobotapocalypse+3
Ekoparty 2025·53 min
Engineers explore architecture and security mechanisms for ARACNE: A Multi-Agent LLM Framework for Comprehensive Autonomous Linux Shell Security Testing.
linuxllmframework+1
Ekoparty Security Conference·28 min
Emilio Oropeza
Investigates from DevSecOps (ML/LLM) SecOps - Emilio Oropeza and evaluates key implications for security practitioners.
llmdevsecopsdevsecop+2