English
Related papers

Related papers: CAPTURE: Context-Aware Prompt Injection Testing an…

200 papers

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Computation and Language · Computer Science 2022-04-12 Lei Xu , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Zhiyuan Liu

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…

Cryptography and Security · Computer Science 2026-04-15 Yulin Chen , Tri Cao , Haoran Li , Yue Liu , Yibo Li , Yufei He , Le Minh Khoi , Yangqiu Song , Shuicheng Yan , Bryan Hooi

The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based…

Computation and Language · Computer Science 2024-02-05 Shuai Zhao , Jinming Wen , Luu Anh Tuan , Junbo Zhao , Jie Fu

The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web…

Machine Learning · Computer Science 2025-11-26 Kaiyuan Zhang , Mark Tenenholtz , Kyle Polley , Jerry Ma , Denis Yarats , Ninghui Li

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning…

Machine Learning · Computer Science 2024-11-12 Tong Chen , Hao Fang , Patrick Xia , Xiaodong Liu , Benjamin Van Durme , Luke Zettlemoyer , Jianfeng Gao , Hao Cheng

Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to capture how safety properties evolve under sustained adversarial interaction. We present ADVERSA,…

Cryptography and Security · Computer Science 2026-03-12 Harry Owiredu-Ashley

We propose a lightweight explainable guardrail (LEG) method to detect unsafe prompts. LEG uses a multi-task learning architecture to jointly learn a prompt classifier and an explanation classifier, where the latter labels prompt words that…

Computation and Language · Computer Science 2026-04-28 Md Asiful Islam , Mihai Surdeanu

Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedded in HTML content or visual interfaces. Existing guard…

Cryptography and Security · Computer Science 2026-05-15 Tri Cao , Yulin Chen , Hieu Cao , Yibo Li , Khoi Le , Thong Nguyen , Yuexin Li , Yufei He , Yue Liu , Shuicheng Yan , Bryan Hooi

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,…

The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust guardrailing systems that ensure safety, reliability, and compliance. Existing solutions…

Computation and Language · Computer Science 2025-10-16 Karthik Avinash , Nikhil Pareek , Rishav Hada

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…

Cryptography and Security · Computer Science 2025-07-15 William Hackett , Lewis Birch , Stefan Trawicki , Neeraj Suri , Peter Garraghan

System prompts have emerged as a critical control surface for specifying the behavior of LLMs in chat and agent settings. Developers depend on system prompts to specify important context, output format, personalities, guardrails, content…

Computation and Language · Computer Science 2025-02-19 Norman Mu , Jonathan Lu , Michael Lavery , David Wagner

When deploying machine learning models in high-stakes robotics applications, the ability to detect unsafe situations is crucial. Early warning systems can provide alerts when an unsafe situation is imminent (in the absence of corrective…

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Computation and Language · Computer Science 2025-04-18 Charlotte Siska , Anush Sankaran

Recent advances in text-to-image generative models have raised concerns about their potential to produce harmful content when provided with malicious input text prompts. To address this issue, two main approaches have emerged: (1)…

Machine Learning · Computer Science 2025-11-13 Jiwoo Shin , Byeonghu Na , Mina Kang , Wonhyeok Choi , Il-Chul Moon

Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reducing unsafe real-world actions: they may synthesize policies…

Machine Learning · Computer Science 2021-12-16 Yecheng Jason Ma , Andrew Shen , Osbert Bastani , Dinesh Jayaraman

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…

Computation and Language · Computer Science 2025-12-16 Darpan Aswal , Céline Hudelot

Camouflage is primarily context-dependent yet current metrics for camouflaged scenarios overlook this critical factor. Instead, these metrics are originally designed for evaluating general or salient objects, with an inherent assumption of…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Chen-Yang Wang , Gepeng Ji , Song Shao , Ming-Ming Cheng , Deng-Ping Fan

In this fast-evolving area of LLMs, our paper discusses the significant security risk presented by prompt injection attacks. It focuses on small open-sourced models, specifically the LLaMA family of models. We introduce novel defense…

Cryptography and Security · Computer Science 2025-12-19 Safwan Shaheer , G. M. Refatul Islam , Mohammad Rafid Hamid , Tahsin Zaman Jilan

The proliferation of large language models has raised growing concerns about their misuse, particularly in cases where AI-generated text is falsely attributed to human authors. Machine-generated content detectors claim to effectively…

Computation and Language · Computer Science 2025-02-11 Brian Tufts , Xuandong Zhao , Lei Li