Related papers: MultiVer: Zero-Shot Multi-Agent Vulnerability Dete…

Checks remain a foundational instrument in the financial ecosystem, facilitating substantial transaction volumes across institutions. However, their continued use also renders them a persistent target for fraud, underscoring the importance…

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…

Automated code vulnerability detection has gained increasing attention in recent years. The deep learning (DL)-based methods, which implicitly learn vulnerable code patterns, have proven effective in vulnerability detection. The performance…

We study risk-sensitive multi-agent reinforcement learning under general-sum Markov games, where agents optimize the entropic risk measure of rewards with possibly diverse risk preferences. We show that using the regret naively adapted from…

Multi-sensor object detection is an active research topic in automated driving, but the robustness of such detection models against missing sensor input (modality missing), e.g., due to a sudden sensor failure, is a critical problem which…

Multi-agent systems, where specialized agents collaborate to solve a shared task hold great potential, from increased modularity to simulating complex environments. However, they also have a major caveat -- a single agent can cause the…

Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM…

Machine unlearning aims to selectively remove specific knowledge from a trained model. Existing approaches, such as Task Arithmetic, fine-tune the model on the forget set to create a task vector (i.e., a direction in weight space) for…

Manual software beta testing is costly and time-consuming, while single-agent large language model (LLM) approaches suffer from hallucinations and inconsistent behavior. We propose a multi-agent committee framework in which diverse…

For the majority of the machine learning community, the expensive nature of collecting high-quality human-annotated data and the inability to efficiently finetune very large state-of-the-art pretrained models on limited compute are major…

The rapid growth of speech synthesis and voice conversion systems has made deepfake audio a major security concern. Bengali deepfake detection remains largely unexplored. In this work, we study automatic detection of Bengali audio deepfakes…

Adversarial machine learning attacks on video action recognition models is a growing research area and many effective attacks were introduced in recent years. These attacks show that action recognition models can be breached in many ways.…

Empowering large language models (LLMs) with effective tool utilization capabilities is crucial for enabling AI agents to solve complex problems. However, current models face two major limitations: (1) unreliable tool planning and…

We identify and formalize a novel security risk: Context-Fragmented Violations (CFVs) - a class of policy breaches where individual agent actions appear locally safe and reasonable, yet collectively violate organizational policies because…

Trustworthiness reasoning aims to enable agents in multiplayer games with incomplete information to identify potential allies and adversaries, thereby enhancing decision-making. In this paper, we introduce the graph retrieval-augmented…

Portfolio backtesting is the primary tool for evaluating investment strategies before deployment, yet practitioners implicitly assume that different engines produce identical results for the same strategy. we formalise implementation risk,…

Machine unlearning aims to remove the influence of specific data points from a trained model to satisfy privacy, copyright, and safety requirements. In real deployments, providers distribute a global model to many edge devices, where each…

Large Language Models (LLMs) have shown promise for automated vulnerability repair (AVR), but they still face several limitations, including the lack of intra-vulnerability experience accumulation and the lack of cross-vulnerability…

Decompilation -- recovering source code from compiled binaries -- is essential for security analysis, malware reverse engineering, and legacy software maintenance. However, existing decompilers produce code that often fails to compile or…

Face morphing attacks threaten biometric verification, yet most morphing attack detection (MAD) systems require task-specific training and generalize poorly to unseen attack types. Meanwhile, open-source multimodal large language models…