Related papers: SnapGuard: Lightweight Prompt Injection Detection …
Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes them to Indirect Prompt Injection (IPI), where attackers embed…
As LLM agents transition from digital assistants to physical controllers in autonomous systems and robotics, they face an escalating threat from indirect prompt injection. By embedding adversarial instructions into the results of tool…
With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…
Large Language Models (LLMs) are increasingly integrated into web-based systems for content summarization, yet their susceptibility to prompt injection attacks remains a pressing concern. In this study, we explore how non-visible HTML…
The existing Multimodal Large Language Models (MLLMs) for GUI perception have made great progress. However, the following challenges still exist in prior methods: 1) They model discrete coordinates based on text autoregressive mechanism,…
Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…
Internet memes have emerged as a popular multimodal medium, yet they are increasingly weaponized to convey harmful opinions through subtle rhetorical devices like irony and metaphor. Existing detection approaches, including Multimodal Large…
Recent studies have demonstrated that machine learning approaches like deep neural networks (DNNs) are easily fooled by adversarial attacks. Subtle and imperceptible perturbations of the data are able to change the result of deep neural…
Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such…
Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across…
Large Language Models have found success in a variety of applications. However, their safety remains a concern due to the existence of various jailbreaking methods. Despite significant efforts, alignment and safety fine-tuning only provide…
Contrastively trained text-image models have the remarkable ability to perform zero-shot classification, that is, classifying previously unseen images into categories that the model has never been explicitly trained to identify. However,…
Large Language Models (LLMs) are increasingly powerful but remain vulnerable to prompt injection attacks, where malicious inputs cause the model to deviate from its intended instructions. This paper introduces Sentinel, a novel detection…
Person re-identification (re-id) models are vital in security surveillance systems, requiring transferable adversarial attacks to explore the vulnerabilities of them. Recently, vision-language models (VLM) based attacks have shown superior…
Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box…
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to address all of these challenges by developing an extremely…
Feature Visualization (FV) is a widely used technique for interpreting concepts learned by Deep Neural Networks (DNNs), which synthesizes input patterns that maximally activate a given feature. Despite its popularity, the trustworthiness of…
Morphing attack detection has become an essential component of face recognition systems for ensuring a reliable verification scenario. In this paper, we present a multimodal learning approach that can provide a textual description of…
The security infrastructure is ill-equipped to detect and deter the smuggling of non-explosive devices that enable terror attacks such as those recently perpetrated in western Europe. The detection of so-called "small metallic threats"…
Current open-source prompt-injection detectors converge on two architectural choices: regular-expression pattern matching and fine-tuned transformer classifiers. Both share failure modes that recent work has made concrete. Regular…