English
Related papers

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

200 papers

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Computation and Language · Computer Science 2025-11-24 Ziqi Miao , Lijun Li , Yuan Xiong , Zhenhua Liu , Pengyu Zhu , Jing Shao

Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…

Cryptography and Security · Computer Science 2025-11-21 Badrinath Ramakrishnan , Akshaya Balaji

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. As a countermeasure, backdoor detection methods…

Computation and Language · Computer Science 2025-09-23 Jun Yan , Wenjie Jacky Mo , Xiang Ren , Robin Jia

Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false…

Cryptography and Security · Computer Science 2024-06-11 Yonatan Amaru , Prasanna Wudali , Yuval Elovici , Asaf Shabtai

Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting,…

Cryptography and Security · Computer Science 2026-05-22 Alexandre Cristovão Maiorano

Current open-source prompt-injection detectors converge on two architectural choices: regular-expression pattern matching and fine-tuned transformer classifiers. Both share failure modes that recent work has made concrete. Regular…

Cryptography and Security · Computer Science 2026-05-19 Thamilvendhan Munirathinam

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

Cryptography and Security · Computer Science 2025-11-12 Zihan Wang , Rui Zhang , Hongwei Li , Wenshu Fan , Wenbo Jiang , Qingchuan Zhao , Guowen Xu

The performance of deep models, including Vision Transformers, is known to be vulnerable to adversarial attacks. Many existing defenses against these attacks, such as adversarial training, rely on full-model fine-tuning to induce robustness…

Machine Learning · Computer Science 2025-02-10 Masih Eskandar , Tooba Imtiaz , Zifeng Wang , Jennifer Dy

Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low…

Computer Vision and Pattern Recognition · Computer Science 2020-11-16 Faisal Alamri , Sinan Kalkan , Nicolas Pugeault

Benefiting from strong and efficient multi-modal alignment strategies, Large Visual Language Models (LVLMs) are able to simulate human visual and reasoning capabilities, such as solving CAPTCHAs. However, existing benchmarks based on visual…

Artificial Intelligence · Computer Science 2025-12-15 Jianyi Zhang , Ziyin Zhou , Xu Ji , Shizhao Liu , Zhangchi Zhao

Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: (1) their effectiveness degrades…

Cryptography and Security · Computer Science 2026-04-02 Yanting Wang , Wei Zou , Runpeng Geng , Jinyuan Jia

Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation…

Computation and Language · Computer Science 2025-08-26 Jun Zhuang , Haibo Jin , Ye Zhang , Zhengjian Kang , Wenbin Zhang , Gaby G. Dagher , Haohan Wang

Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their robustness against sophisticated adversarial attacks remains poorly characterized. This study…

Cryptography and Security · Computer Science 2025-12-01 Richard J. Young

In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction…

Machine Learning · Computer Science 2026-05-28 Amir Moeini , Minjae Kwon , Alper Kamil Bozkurt , Yuichi Motai , Rohan Chandra , Lu Feng , Shangtong Zhang

Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…

Computation and Language · Computer Science 2025-05-29 Xiaofei Wen , Wenxuan Zhou , Wenjie Jacky Mo , Muhao Chen

The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task. While it may be tempting to simply choose a prompt based on average performance on a…

Machine Learning · Computer Science 2024-03-29 Thomas P. Zollo , Todd Morrill , Zhun Deng , Jake C. Snell , Toniann Pitassi , Richard Zemel

Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard safety objectives. To address this gap, we introduce…

Artificial Intelligence · Computer Science 2026-05-20 Xiaofei Wen , Wenjie Jacky Mo , Yanan Xie , Peng Qi , Muhao Chen

With the rapid advancement of AI models, their deployment across diverse tasks has become increasingly widespread. A notable emerging application is leveraging AI models to assist in reviewing scientific papers. However, recent reports have…

Computation and Language · Computer Science 2025-11-04 Qin Zhou , Zhexin Zhang , Zhi Li , Limin Sun

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples.…

Computation and Language · Computer Science 2023-04-03 Huan Ma , Changqing Zhang , Yatao Bian , Lemao Liu , Zhirui Zhang , Peilin Zhao , Shu Zhang , Huazhu Fu , Qinghua Hu , Bingzhe Wu

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Machine Learning · Computer Science 2022-11-02 Ganqu Cui , Lifan Yuan , Bingxiang He , Yangyi Chen , Zhiyuan Liu , Maosong Sun