Related papers: Hidden Ghost Hand: Unveiling Backdoor Vulnerabilit…

The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already functions as…

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing…

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Mobile GUI agents can automate smartphone tasks by interacting directly with app interfaces, but how they should communicate with users during execution remains underexplored. Existing systems rely on two extremes: foreground execution,…

We surface a new threat to closed-weight Large Language Models (LLMs) that enables an attacker to compute optimization-based prompt injections. Specifically, we characterize how an attacker can leverage the loss-like information returned…

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions…

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose…

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,…

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…

Insider threats pose a persistent and critical security risk, yet are notoriously difficult to detect in complex enterprise environments, where malicious actions are often hidden within seemingly benign user behaviors. Although…

With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their complex reasoning processes introduce new and largely unexplored…

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly…

While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…