相关论文: Dual-Modality Multi-Stage Adversarial Safety Train…

Multi-agent debate (MAD) systems leverage collective intelligence to enhance reasoning capabilities, yet existing approaches struggle to simultaneously optimize accuracy, consensus formation, and computational efficiency. Static topology…

Recent advances in deep learning have markedly improved autonomous driving (AD) models, particularly end-to-end systems that integrate perception, prediction, and planning stages, achieving state-of-the-art performance. However, these…

The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation. However, the security…

Autonomous cars are well known for being vulnerable to adversarial attacks that can compromise the safety of the car and pose danger to other road users. To effectively defend against adversaries, it is required to not only test autonomous…

Attack-Defence Trees (ADTs) are well-suited to assess possible attacks to systems and the efficiency of counter-measures. In this paper, we first enrich the available constructs with reactive patterns that cover further security scenarios,…

With the advancement of vision transformers (ViTs) and self-supervised learning (SSL) techniques, pre-trained large ViTs have become the new foundation models for computer vision applications. However, studies have shown that, like…

As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either restricted to a narrow…

The integration of Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) into mobile GUI agents has significantly enhanced user efficiency and experience. However, this advancement also introduces potential security…

This paper introduces an attacking mechanism to challenge the resilience of autonomous driving systems. Specifically, we manipulate the decision-making processes of an autonomous vehicle by dynamically displaying adversarial patches on a…

Multimodal large language models (MLLMs) have shown strong capability in semantic understanding and visual reasoning, yet their use on continuous video streams in bandwidth-constrained edge-cloud systems incurs prohibitive computation and…

Since the advent of large language models, prompt engineering now enables the rapid, low-effort creation of diverse autonomous agents that are already in widespread use. Yet this convenience raises urgent concerns about the safety,…

Recent advances in Competitive Self-Play (CSP) have achieved, or even surpassed, human level performance in complex game environments such as Dota 2 and StarCraft II using Distributed Multi-Agent Reinforcement Learning (MARL). One core…

Deep learning-based adversarial malware detectors have yielded promising results in detecting never-before-seen malware executables without relying on expensive dynamic behavior analysis and sandbox. Despite their abilities, these detectors…

Multi-agent collaboration involves multiple participants working together in a shared environment to achieve a common goal. These agents share information, divide tasks, and synchronize their actions. Key aspects of multi agent…

Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving contexts and strategically adapting opponents. Such environments are inherently…

Multi-Armed Bandit (MAB) systems are witnessing an upswing in applications within multi-agent distributed environments, leading to the advancement of collaborative MAB algorithms. In such settings, communication between agents executing…

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat…

Domain adversarial training has been ubiquitous for achieving invariant representations and is used widely for various domain adaptation tasks. In recent times, methods converging to smooth optima have shown improved generalization for…

Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfect and deceptive information. In this paper, we study a…

The current cybersecurity landscape is increasingly complex, with traditional Static Application Security Testing (SAST) tools struggling to capture complex and emerging vulnerabilities due to their reliance on rule-based matching.…