相关论文: PromptArmor: Simple yet Effective Prompt Injection…

Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies,…

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…

Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data to produce triage labels, incident summaries, or remediation advice. We study a structural…

The integration of Large Language Models (LLMs) with external sources is becoming increasingly common, with Retrieval-Augmented Generation (RAG) being a prominent example. However, this integration introduces vulnerabilities of Indirect…

Following the advancement of large language models (LLMs), the development of LLM-based autonomous agents has become increasingly prevalent. As a result, the need to understand the security vulnerabilities of these agents has become a…

While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable to prompt injection attacks: malicious third party prompts that subvert the intent of the system designer. To help researchers…

Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this…

A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data. We evaluate…

Multimodal agents built on large vision-language models (LVLMs) are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection, especially through visual inputs. We introduce AgentTypo, a black-box…

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions,…

Computer-use agents are increasingly capable of operating on real operating systems, but this capability has also increased the risks posed by prompt injection, indirect instructions, and visual attacks. Existing defenses typically rely on…

Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.…

The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these…

The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-dependent nature of attacks, however, current defenses are…

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…

Prompt injection attacks pose a significant challenge to the safe deployment of Large Language Models (LLMs) in real-world applications. While prompt-based detection offers a lightweight and interpretable defense strategy, its effectiveness…

Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user…