Applied GAI in Security

Sign in Subscribe

Latest

Last Week in GAI Security Research - 08/05/24

Last Week in GAI Security Research - 08/05/24

Highlights from Last Week * 🧑‍⚖ Jailbreaking Text-to-Image Models with LLM-Based Agents * 🎣 From ML to LLM: Evaluating the Robustness of Phishing Webpage Detection Models against Adversarial Attacks * 🤖 The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies * 🔊 Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification * 🏋🏼 Tamper-Resistant Safeguards for

Last Week in GAI Security Research - 07/29/24

Last Week in GAI Security Research - 07/29/24

Highlights from Last Week * 🔴 RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent * 🩺 CVE-LLM : Automatic vulnerability evaluation in medical device industry using large language models * ❤‍🩹 PenHeal: A Two-Stage LLM Framework for Automated Pentesting and Optimal Remediation * 📚 Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs) * 🖐🏻 LLMmap: Fingerprinting

Last Week in GAI Security Research - 07/22/24

Last Week in GAI Security Research - 07/22/24

🎰 Blackhat 2024 is coming up on August 3-8th! If you intend to be in Las Vegas for the annual security conference and want to discuss generative AI applied to security use cases, send me an email. I will be speaking on one of the panels in the AI Summit and

Last Week in GAI Security Research - 07/15/24

Last Week in GAI Security Research - 07/15/24

Highlights from Last Week * 😎 A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends * 🛍 On the (In)Security of LLM App Stores * 🦠 Tactics, Techniques, and Procedures (TTPs) in Interpreted Malware: A Zero-Shot Generation with Large Language Models * ⚠️ eyeballvul: a future-proof benchmark for vulnerability detection in the wild

Last Week in GAI Security Research - 07/08/24

Last Week in GAI Security Research - 07/08/24

Highlights from Last Week * 🪤 JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasets * 🦙 Badllama 3: removing safety finetuning from Llama 3 in minutes * 🖇 Actionable Cyber Threat Intelligence using Knowledge Graphs and Large Language Models * 🧑‍💻 Enhancing the Capability and Robustness of Large Language Models through Reinforcement

Last Week in GAI Security Research - 07/01/24

Last Week in GAI Security Research - 07/01/24

Highlights from Last Week * 🪱 Synthetic Cancer – Augmenting Worms with LLMs * 🔗 Large Language Models for Link Stealing Attacks Against Graph Neural Networks * 🧑‍💻 Assessing the Effectiveness of LLMs in Android Application Vulnerability Analysis * 🦠 MALSIGHT: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization * 🦜 Poisoned LangChain: Jailbreak LLMs by LangChain

Last Week in GAI Security Research - 06/24/24

Last Week in GAI Security Research - 06/24/24

Highlights from Last Week * 🥷🏿 AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents * 🐵 From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking * 💰 Jailbreaking as a Reward Misspecification Problem * 🏹 "Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models'