Related papers: Evolutionary Multi-Task Injection Testing on Web A…

The Update Framework or TUF was developed to address several known weaknesses that have been observed in software update distribution and validation systems. Unlike conventional secure software distribution methods where there may be a…

This paper introduces a methodological framework for empirically testing AI alignment strategies through structured multi-model dialogue. Drawing on Peace Studies traditions - particularly interest-based negotiation, conflict…

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the…

To effectively test complex software, it is important to generate goal-specific inputs, i.e., inputs that achieve a specific testing goal. However, most state-of-the-art test generators are not designed to target specific goals. Notably,…

Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream architecture opens an underexplored attack surface: an adversary who injects…

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…

Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to enhance its security, but they achieve limited…

With the growing popularity of Android devices, Android malware is seriously threatening the safety of users. Although such threats can be detected by deep learning as a service (DLaaS), deep neural networks as the weakest part of DLaaS are…

In this work, we investigate the concept of biometric backdoors: a template poisoning attack on biometric systems that allows adversaries to stealthily and effortlessly impersonate users in the long-term by exploiting the template update…

WebAssembly (Wasm) is a low-level binary format for web applications, which has found widespread adoption due to its improved performance and compatibility with existing software. However, the popularity of Wasm has also led to its…

The modern web stack, which is dominated by browser-based applications and API-first backends, now operates under an adversarial equilibrium where automated, AI-assisted attacks evolve continuously. Content Delivery Networks (CDNs) and edge…

Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parameter updates, and reusable components opens entry points for attackers. Threats have…

Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. While numerous defenses aiming to improve the robustness have…

AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where…

In recent years, machine learning models, especially deep neural networks, have been widely used for classification tasks in the security domain. However, these models have been shown to be vulnerable to adversarial manipulation: small…

Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical in order to ensure the safety and robustness of critical AI…

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus…

Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs. Existing…

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional context modeling. Yet their security implications,…

The success of deep learning has enabled advances in multimodal tasks that require non-trivial fusion of multiple input domains. Although multimodal models have shown potential in many problems, their increased complexity makes them more…