Related papers: AWE: Adaptive Agents for Dynamic Web Penetration T…
Machine Learning (ML) has become the new contrivance in almost every field. This makes them a target of fraudsters by various adversary attacks, thereby hindering the performance of ML models. Evasion and Data-Poison-based attacks are well…
Software vulnerabilities continue to be ubiquitous, even in the era of AI-powered code assistants, advanced static analysis tools, and the adoption of extensive testing frameworks. It has become apparent that we must not simply prevent…
One of the most important obligations of privacy-enhancing technologies is to bring confidentiality and privacy to users' browsing activities on the Internet. The website fingerprinting attack enables a local passive eavesdropper to predict…
This work introduces a novel method for enhancing confidence in anomaly detection in Intrusion Detection Systems (IDS) through the use of a Variational Autoencoder (VAE) architecture. By developing a confidence metric derived from latent…
Training state-of-the-art vision models has become prohibitively expensive for researchers and practitioners. For the sake of accessibility and resource reuse, it is important to focus on adapting these models to a variety of downstream…
Modern software package registries like PyPI have become critical infrastructure for software development, but are increasingly exploited by threat actors distributing malicious packages with sophisticated multi-stage attack chains. While…
Repository-level fault localization (FL) and automated program repair (APR) require an agent to identify the relevant code units across files, follow call and data dependencies, and generate a valid patch. Existing graph-based systems…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
The adoption of Internet of Things (IoT) systems at the network edge of smart architectures is increasing rapidly, intensifying the need for security mechanisms that are both adaptive and resource-efficient. In such environments, runtime…
Modern commercial antivirus systems increasingly rely on machine learning to keep up with the rampant inflation of new malware. However, it is well-known that machine learning models are vulnerable to adversarial examples (AEs). Previous…
Coding agents powered by large language models (LLMs) have gained traction for automating code generation through iterative problem-solving with minimal human involvement. Despite the emergence of various frameworks, e.g., LangChain,…
Autonomous LLM agents operate as long-running processes with persistent workspaces, memory files, scheduled task state, and messaging integrations. These features create a new propagation risk: attacker-influenced content can be written…
The Internet of Agents is propelling edge computing toward agentic AI and edge general intelligence (EGI). However, deploying multi-agent service (MAS) on resource-constrained edge infrastructure presents severe challenges. MAS service…
Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under realistic conditions: binary-only feedback, no gradient…
Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…
Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…
The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…
Large language models (LLMs) are transforming automated program repair (APR) through agent-based approaches that localize bugs, generate patches, and verify fixes. However, the lack of high-quality, scalable training datasets, especially…
Web agents promise to automate complex browser tasks, but current methods remain brittle -- relying on step-by-step UI interactions and heavy LLM reasoning that break under dynamic layouts and long horizons. Humans, by contrast, exploit…
Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current…