Challenge: Large Language Models (LLMs) agents use external tools to interact with environments, but they also introduce security risks, such as indirect prompt injection (IPI) attacks.
Approach: They evaluate eight different defenses and bypass all of them using adaptive attacks.
Outcome: The proposed defenses achieve an attack success rate of over 50% and are robust against adaptive attacks.

Similar Papers

The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration (2025.emnlp-demos)

Copied to clipboard

Challenge: Large Language Model (LLM)-integrated applications are becoming more popular to support, augment, and automate tasks.
Approach: They propose to embed universal adversarial triggers in webpage HTML to hijack agents . they also use a browser-gym agent powered by Llama-3.1 to test their system .
Outcome: The proposed system software is released under the MIT License .
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents (2024.findings-acl)

Copied to clipboard

Challenge: Recent work has embodied LLMs as agents, but external content introduces the risk of indirect prompt injection (IPI) attacks.
Approach: They propose a benchmark to assess the vulnerability of tool-integrated LLM agents to IPI attacks.
Outcome: The proposed benchmark assesses the vulnerability of tool-integrated LLM agents to IPI attacks.
Defending against Indirect Prompt Injection by Instruction Detection (2025.findings-emnlp)

Copied to clipboard

Challenge: Indirect Prompt Injection attacks can be exploited by LLMs that are embedded with external data.
Approach: They propose a detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.
Outcome: The proposed approach reduces the success rate of attacks to 0.03% on the BIPIA benchmark.
Defense Against Prompt Injection Attack by Leveraging Attack Techniques (2025.acl-long)

Copied to clipboard

Challenge: Recent attacks leverage LLMs’ instruction-following abilities and their inabilities to distinguish instructions injected in the data content.
Approach: They invert the intention of prompt injection methods to develop novel defense methods based on previous training-free attack methods by repeating the attack process with the original input instruction rather than the injected instruction.
Outcome: The proposed methods outperform existing defense approaches, achieving state-of-the-art results.
Rethinking Assessments of Prompt Injection Attacks (2026.findings-acl)

Copied to clipboard

Challenge: Prompt injection attacks are recognized as one of the primary risks faced by LLM-integrated applications in recent years.
Approach: They evaluate prompt injection attacks on LLM-integrated applications across 37 target tasks, 185 injected tasks, 21 attack instructions, and 143,745 queries.
Outcome: The proposed framework provides a solid foundation for assessing vulnerabilities in LLM-integrated applications and evaluating the efficacy of defensive strategies.
From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been explored for automating or enhancing penetration testing tasks, but their effectiveness and reliability remain open questions.
Approach: They evaluate multiple LLM-based agents across realistic penetration testing scenarios . they also examine impact of core functional capabilities on agent success .
Outcome: The proposed models improve agent performance in multi-step and real-time penetration testing scenarios.
Conjunctive Prompt Attacks in Multi-Agent LLM Systems (2026.acl-long)

Copied to clipboard

Challenge: Existing defenses do not reliably stop the attack because no single component appears malicious in isolation.
Approach: They study conjunctive prompt attacks where trigger key and adversarial template appear benign alone but activate harmful behavior when routing brings them together.
Outcome: The proposed model significantly improves performance over baselines while keeping false activations low.
Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition (2023.emnlp-main)

Copied to clipboard

Challenge: Large Language Models are increasingly being deployed in interactive contexts that involve direct user engagement.
Approach: They run a global prompt hacking competition to encourage research on prompt hacks . they elicit 600K+ adversarial prompts against three state-of-the-art LLMs based on a dataset .
Outcome: The results of the competition show that current LLMs can be manipulated via prompt hacking . the competition elicits 600K+ adversarial prompts against three state-of-the-art LLM models .
Can Indirect Prompt Injection Attacks Be Detected and Removed? (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have developed various detection mechanisms to protect against prompt injection attacks.
Approach: They investigate the feasibility of detecting and removing indirect prompt injection attacks . they use two methods to evaluate their performance and train detection models .
Outcome: The proposed method is based on a benchmark dataset and is available on github . it evaluates the performance of existing models and open-source detection models .
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents (2025.acl-long)

Copied to clipboard

Challenge: Large Language Model (LLM) agents are becoming conversational assistants . indirect prompt injection attacks pose a critical threat to these systems .
Approach: They propose a novel and orthogonal perspective that reframes agent security . they propose 'task shield' that verifies whether each instruction and tool call contributes to user objectives .
Outcome: The proposed defense reduces attack success rates while maintaining high task utility on the AgentDojo benchmark.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations