Vulnerability Mitigation System (VMS): LLM Agent and Evaluation Framework for Autonomous Penetration Testing

As the frequency of cyber threats increases, conventional penetration testing is failing to capture the entirety of todays complex environments. To solve this problem, we propose the Vulnerability Mitigation System VMS, a novel agent based on a Large Language Model LLM capable of performing...

When Developer Aid Becomes Security Debt: a Systematic Analysis of Insecure Behaviors in LLM Coding Agents

LLM-based coding agents are rapidly being deployed in software development, yet their security implications remain poorly understood. These agents, while capable of accelerating software development, may inadvertently introduce insecure practices. We conducted the first systematic security...

The Dark Side of LLMs Agent-Based Attacks for Complete Computer Takeover

The rapid adoption of Large Language Model LLM agents and multi-agent systems enables unprecedented capabilities in natural language processing and generation. However, these systems have introduced unprecedented security vulnerabilities that extend beyond traditional prompt injection attacks. Th...

Agent Safety Alignment Via Reinforcement Learning

The emergence of autonomous Large Language Model LLM agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to both user-initiated threats e.g., adversarial prompts and...

AI Agent Smart Contract Exploit Generation

We present A1, an agentic execution driven system that transforms any LLM into an end-to-end exploit generator. A1 has no hand-crafted heuristics and provides the agent with six domain-specific tools that enable autonomous vulnerability discovery. The agent can flexibly leverage these tools to...

Palo Alto Networks Autonomous Digital Experience 安全漏洞

Palo Alto Networks Autonomous Digital Experience is a digital experience monitoring and optimization software from Palo Alto, USA. A security vulnerability exists in Palo Alto Networks Autonomous Digital Experience that stems from an improper privilege assignment that could result in a locally...

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs

Large Language Models LLMs for code generation i.e., Code LLMs have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating vulnerable or even malicious code under adversarial settings...

Reversing the Paradigm: Building AI-First Systems with Human Guidance

The relationship between humans and artificial intelligence is no longer science fiction -- it's a growing reality reshaping how we live and work. AI has moved beyond research labs into everyday life, powering customer service chats, personalizing travel, aiding doctors in diagnosis, and supporti...

Algorithmic Approaches to Enhance Safety in Autonomous Vehicles: Minimizing Lane Changes and Merging

The rapid advancements in autonomous vehicle AV technology promise enhanced safety and operational efficiency. However, frequent lane changes and merging maneuvers continue to pose significant safety risks and disrupt traffic flow. This paper introduces the Minimizing Lane Change Algorithm MLCA, ...

AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models

We introduce AIRTBench, an AI red teaming benchmark for evaluating language models' ability to autonomously discover and exploit Artificial Intelligence and Machine Learning AI/ML security vulnerabilities. The benchmark consists of 70 realistic black-box capture-the-flag CTF challenges from the...

Autonomous 3D Moving Target Encirclement and Interception with Range Measurement

Commercial UAVs are an emerging security threat as they are capable of carrying hazardous payloads or disrupting air traffic. To counter UAVs, we introduce an autonomous 3D target encirclement and interception strategy. Unlike traditional ground-guided systems, this strategy employs autonomous...

Massive 7.3 Tbps DDoS Attack Delivers 37.4 TB in 45 Seconds, Targeting Hosting Provider

Cloudflare on Thursday said it autonomously blocked the largest distributed denial-of-service DDoS attack ever recorded, which hit a peak of 7.3 terabits per second Tbps. The attack, which was detected in mid-May 2025, targeted an unnamed hosting provider. "Hosting providers and critical Internet...

Training RL Agents for Multi-Objective Network Defense Tasks

Open-ended learning OEL -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence AI agents to achieve robustness and generalization. However, despite promising results that demonstrate the benefits of...

One Patch to Rule Them All: Transforming Static Patches into Dynamic Attacks in the Physical World

Numerous methods have been proposed to generate physical adversarial patches PAPs against real-world machine learning systems. However, each existing PAP typically supports only a single, fixed attack goal, and switching to a different objective requires re-generating and re-deploying a new PAP...

5 Things Security Leaders Need to Know About Agentic AI

From writing assistance to intelligent summarization, generative AI has already transformed the way businesses work. But we’re now entering a new phase where AI doesn’t just generate content, but takes independent action on our behalf. This next evolution is called ‘agentic AI’, and it’s moving...

COALESCE: Economic and Security Dynamics of Skill-Based Task Outsourcing among Team of Autonomous LLM Agents

The meteoric rise and proliferation of autonomous Large Language Model LLM agents promise significant capabilities across various domains. However, their deployment is increasingly constrained by substantial computational demands, specifically for Graphics Processing Unit GPU resources. This pape...

Security Concerns for Large Language Models: a Survey

Large Language Models LLMs such as GPT-4 and its recent iterations, Google's Gemini, Anthropic's Claude 3 models, and xAI's Grok have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities. In this survey, we provide a comprehensive...

Blockchain Powered Edge Intelligence for U-Healthcare in Privacy Critical and Time Sensitive Environment

Edge Intelligence EI serves as a critical enabler for privacy-preserving systems by providing AI-empowered computation and distributed caching services at the edge, thereby minimizing latency and enhancing data privacy. The integration of blockchain technology further augments EI frameworks by...

Preventing Adversarial AI Attacks against Autonomous Situational Awareness: a Maritime Case Study

Adversarial artificial intelligence AI attacks pose a significant threat to autonomous transportation, such as maritime vessels, that rely on AI components. Malicious actors can exploit these systems to deceive and manipulate AI-driven operations. This paper addresses three critical research...

Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems

Autonomous driving systems ADS increasingly rely on deep learning-based perception models, which remain vulnerable to adversarial attacks. In this paper, we revisit adversarial attacks and defense methods, focusing on road sign recognition and lead object detection and prediction e.g., relative...