Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks

Large Language Model (LLM)-based agents with function-calling capabilities are increasingly deployed, but remain vulnerable to Indirect Prompt Injection (IPI) attacks that hijack their tool calls. In response, numerous IPI-centric defense frameworks have emerged. However, these defenses are fragmented, lacking a unified taxonomy and comprehensive evaluation. In this Systematization of Knowledge (SoK), we present the first comprehensive analysis of IPI-centric defense frameworks. We introduce a comprehensive taxonomy of these defenses, classifying them along five dimensions. We then thoroughly assess the security and usability of representative defense frameworks. Through analysis of defensive failures in the assessment, we identify six root causes of defense circumvention. Based on these findings, we design three novel adaptive attacks that significantly improve attack success rates targeting specific frameworks, demonstrating the severity of the flaws in these defenses. Our paper provides a foundation and critical insights for the future development of more secure and usable IPI-centric agent defense frameworks.

Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning

Retrieval-Augmented Generation (RAG) has become a standard approach for improving the reliability of large language models (LLMs). Prior work demonstrates the vulnerability of RAG systems by misleading them into generating attacker-chosen outputs through poisoning the knowledge base. However, this paper uncovers that such attacks could be mitigated by the strong \textit{self-correction ability (SCA)} of modern LLMs, which can reject false context once properly configured. This SCA poses a significant challenge for attackers aiming to manipulate RAG systems. In contrast to previous poisoning methods, which primarily target the knowledge base, we introduce \textsc{DisarmRAG}, a new poisoning paradigm that compromises the retriever itself to suppress the SCA and enforce attacker-chosen outputs. This compromisation enables the attacker to straightforwardly embed anti-SCA instructions into the context provided to the generator, thereby bypassing the SCA. To this end, we present a contrastive-learning-based model editing technique that performs localized and stealthy edits, ensuring the retriever returns a malicious instruction only for specific victim queries while preserving benign retrieval behavior. To further strengthen the attack, we design an iterative co-optimization framework that automatically discovers robust instructions capable of bypassing prompt-based defenses. We extensively evaluate DisarmRAG across six LLMs and three QA benchmarks. Our results show near-perfect retrieval of malicious instructions, which successfully suppress SCA and achieve attack success rates exceeding 90\% under diverse defensive prompts. Also, the edited retriever remains stealthy under several detection methods, highlighting the urgent need for retriever-centric defenses.

SoK: Evaluating Jailbreak Guardrails for Large Language Models

Large Language Models (LLMs) have achieved remarkable progress, but their deployment has exposed critical vulnerabilities, particularly to jailbreak attacks that circumvent safety mechanisms. Guardrails--external defense mechanisms that monitor and control LLM interaction--have emerged as a promising solution. However, the current landscape of LLM guardrails is fragmented, lacking a unified taxonomy and comprehensive evaluation framework. In this Systematization of Knowledge (SoK) paper, we present the first holistic analysis of jailbreak guardrails for LLMs. We propose a novel, multi-dimensional taxonomy that categorizes guardrails along six key dimensions, and introduce a Security-Efficiency-Utility evaluation framework to assess their practical effectiveness. Through extensive analysis and experiments, we identify the strengths and limitations of existing guardrail approaches, explore their universality across attack types, and provide insights into optimizing defense combinations. Our work offers a structured foundation for future research and development, aiming to guide the principled advancement and deployment of robust LLM guardrails. The code is available at https://github.com/xunguangwang/SoK4JailbreakGuardrails.

Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models

This position paper proposes a fundamental shift in designing code generation models: treating reasoning depth as a controllable resource. Rather than being an incidental byproduct of prompting, we argue that the trade-off between rapid, direct answers ("fast thinking") and elaborate, chain-of-thought deliberation ("slow thinking") must be explicitly managed. We contend that optimizing reasoning budgets across the entire model lifecycle - from synthetic data creation and benchmarking to real-world deploymen - can unlock superior trade-offs among accuracy, latency, and cost. This paper outlines how adaptive control over reasoning can enrich supervision signals, motivate new multi-dimensional benchmarks, and inform cost-aware, security-conscious deployment policies. By viewing fast and slow thinking as complementary modes to be scheduled, we envision coding agents that think deep when necessary and act fast when possible.

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

The rapid advancement of Large Language Models (LLMs) has led to the emergence of Multi-Agent Systems (MAS) to perform complex tasks through collaboration. However, the intricate nature of MAS, including their architecture and agent interactions, raises significant concerns regarding intellectual property (IP) protection. In this paper, we introduce MASLEAK, a novel attack framework designed to extract sensitive information from MAS applications. MASLEAK targets a practical, black-box setting, where the adversary has no prior knowledge of the MAS architecture or agent configurations. The adversary can only interact with the MAS through its public API, submitting attack query $q$ and observing outputs from the final agent. Inspired by how computer worms propagate and infect vulnerable network hosts, MASLEAK carefully crafts adversarial query $q$ to elicit, propagate, and retain responses from each MAS agent that reveal a full set of proprietary components, including the number of agents, system topology, system prompts, task instructions, and tool usages. We construct the first synthetic dataset of MAS applications with 810 applications and also evaluate MASLEAK against real-world MAS applications, including Coze and CrewAI. MASLEAK achieves high accuracy in extracting MAS IP, with an average attack success rate of 87% for system prompts and task instructions, and 92% for system architecture in most cases. We conclude by discussing the implications of our findings and the potential defenses.

NAMET: Robust Massive Model Editing via Noise-Aware Memory Optimization

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical metrics or in context-rich settings. We attribute these failures to embedding collisions among knowledge items, which undermine editing reliability at scale. To address this, we propose NAMET (Noise-aware Model Editing in Transformers), a simple yet effective method that introduces noise during memory extraction via a one-line modification to MEMIT. Extensive experiments across six LLMs and three datasets demonstrate that NAMET consistently outperforms existing methods when editing thousands of facts.

GuidedBench: Equipping Jailbreak Evaluation with Guidelines

Jailbreaking methods for large language models (LLMs) have gained increasing attention for building safe and responsible AI systems. After analyzing 35 jailbreak methods across six categories, we find that existing benchmarks, relying on universal LLM-based or keyword-matching scores, lack case-specific criteria, leading to conflicting results. In this paper, we introduce a more robust evaluation framework for jailbreak methods, with a curated harmful question dataset, detailed case-by-case evaluation guidelines, and a scoring system equipped with these guidelines. Our experiments show that existing jailbreak methods exhibit better discrimination when evaluated using our benchmark. Some jailbreak methods that claim to achieve over 90% attack success rate (ASR) on other benchmarks only reach a maximum of 30.2% on our benchmark, providing a higher ceiling for more advanced jailbreak research; furthermore, using our scoring system reduces the variance of disagreements between different evaluator LLMs by up to 76.33%. This demonstrates its ability to provide more fair and stable evaluation.

API-guided Dataset Synthesis to Finetune Large Code Models

Large code models (LCMs), pre-trained on vast code corpora, have demonstrated remarkable performance across a wide array of code-related tasks. Supervised fine-tuning (SFT) plays a vital role in aligning these models with specific requirements and enhancing their performance in particular domains. However, synthesizing high-quality SFT datasets poses a significant challenge due to the uneven quality of datasets and the scarcity of domain-specific datasets. Inspired by APIs as high-level abstractions of code that encapsulate rich semantic information in a concise structure, we propose DataScope, an API-guided dataset synthesis framework designed to enhance the SFT process for LCMs in both general and domain-specific scenarios. DataScope comprises two main components: Dsel and Dgen. On one hand, Dsel employs API coverage as a core metric, enabling efficient dataset synthesis in general scenarios by selecting subsets of existing (uneven-quality) datasets with higher API coverage. On the other hand, Dgen recasts domain dataset synthesis as a process of using API-specified high-level functionality and deliberately-constituted code skeletons to synthesize concrete code. Extensive experiments demonstrate DataScope's effectiveness, with models fine-tuned on its synthesized datasets outperforming those tuned on unoptimized datasets five times larger. Furthermore, a series of analyses on model internals, relevant hyperparameters, and case studies provide additional evidence for the efficacy of our proposed methods. These findings underscore the significance of dataset quality in SFT and advance the field of LCMs by providing an efficient, cost-effective framework for constructing high-quality datasets. This contribution enhances performance across both general and domain-specific scenarios, paving the way for more powerful and tailored LCMs.

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into four major categories: optimization-based attacks such as Greedy Coordinate Gradient (GCG), jailbreak template-based attacks such as "Do-Anything-Now", advanced indirect attacks like DrAttack, and multilingual jailbreaks. However, delivering a practical jailbreak defense is challenging because it needs to not only handle all the above jailbreak attacks but also incur negligible delay to user prompts, as well as be compatible with both open-source and closed-source LLMs. Inspired by how the traditional security concept of shadow stacks defends against memory overflow attacks, this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes a shadow LLM defense instance to concurrently protect the target LLM instance in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs (both target and defense LLMs) have the capability to identify harmful prompts or intentions in user queries, which we empirically validate using the commonly used GPT-3.5/4 models across all major jailbreak attacks. Our measurements show that SelfDefend enables GPT-3.5 to suppress the attack success rate (ASR) by 8.97-95.74% (average: 60%) and GPT-4 by even 36.36-100% (average: 83%), while incurring negligible effects on normal queries. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. These models outperform four SOTA defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. We also empirically show that the tuned models are robust to targeted GCG and prompt injection attacks.

Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs

Agents based on large language models (LLMs) have demonstrated effectiveness in solving a wide range of tasks by integrating LLMs with key modules such as planning, memory, and tool usage. Increasingly, customers are adopting LLM agents across a variety of commercial applications critical to reliability, including support for mental well-being, chemical synthesis, and software development. Nevertheless, our observations and daily use of LLM agents indicate that they are prone to making erroneous plans, especially when the tasks are complex and require long-term planning. In this paper, we propose PDoctor, a novel and automated approach to testing LLM agents and understanding their erroneous planning. As the first work in this direction, we formulate the detection of erroneous planning as a constraint satisfiability problem: an LLM agent's plan is considered erroneous if its execution violates the constraints derived from the user inputs. To this end, PDoctor first defines a domain-specific language (DSL) for user queries and synthesizes varying inputs with the assistance of the Z3 constraint solver. These synthesized inputs are natural language paragraphs that specify the requirements for completing a series of tasks. Then, PDoctor derives constraints from these requirements to form a testing oracle. We evaluate PDoctor with three mainstream agent frameworks and two powerful LLMs (GPT-3.5 and GPT-4). The results show that PDoctor can effectively detect diverse errors in agent planning and provide insights and error characteristics that are valuable to both agent developers and users. We conclude by discussing potential alternative designs and directions to extend PDoctor.