Related papers: Structured Security Auditing and Robustness Enhanc…

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

The integration of Large Language Models (LLMs) into mobile and software development workflows faces a persistent tension among three demands: semantic awareness, developer productivity, and data privacy. Traditional cloud-based tools offer…

Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected gradient masking. We make two contributions. (1) Structured synthesis. We analyze nine…

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…

As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent \textbf{Coordination Engineering}, the ability to codify and systematically improve how multiple agents collaborate…

The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent message interactions. While existing supervised…

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…

Large language models (LLMs) for code generation are typically evaluated on functional correctness alone, overlooking whether generated code propagates harmful content embedded in the prompt. Prior work has shown that most Code LLMs…

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…

Trojanized software packages used in software supply chain attacks constitute an emerging threat. Unfortunately, there is still a lack of scalable approaches that allow automated and timely detection of malicious software packages and thus…

The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently understood. Through comparative experiments…

Modern software systems are increasingly developed within rapid continuous integration and deployment (CI/CD) pipelines, where ensuring security prior to release presents significant technical and organizational challenges. Traditional…

Despite advancements in enhancing LLM safety against jailbreak attacks, evaluating LLM defenses remains a challenge, with current methods often lacking explainability and generalization to complex scenarios, leading to incomplete…

Current safety mechanisms for Large Language Models (LLMs) rely heavily on static, fine-tuned classifiers that suffer from adaptation rigidity, the inability to enforce new governance rules without expensive retraining. To address this, we…

Large Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based methods primarily store raw trajectories, which are often…

As autonomous code agents move toward end-to-end software development, evaluating their practical autonomy becomes critical. Current benchmarks hide friction by testing agents in pre-configured environments, and their static evaluation…

Recent advancements in tool-equipped Agents (LLMs) have enabled complex tasks like secure database interactions and multi-agent code development. However, scaling tool capacity beyond agent reasoning or model limits remains a challenge. In…

The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly rely on visual cues and lack evidence-based reasoning to…

Scaling vision-language models into Visual Multiagent Systems (VMAS) is hindered by two coupled issues. First, communication topologies are fixed before inference, leaving them blind to visual content and query context; second, agent…