English
Related papers

Related papers: RedHerring Attack: Testing the Reliability of Atta…

200 papers

In this article I describe a research agenda for securing machine learning models against adversarial inputs at test time. This article does not present results but instead shares some of my thoughts about where I think that the field needs…

Machine Learning · Computer Science 2019-03-18 Ian Goodfellow

With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the security of LLMs in math solving ability. Instead of attacking…

Computation and Language · Computer Science 2023-09-06 Zihao Zhou , Qiufeng Wang , Mingyu Jin , Jie Yao , Jianan Ye , Wei Liu , Wei Wang , Xiaowei Huang , Kaizhu Huang

Characterizing attacker behavior with respect to Cyber-Physical Systems is important to assuring the security posture and resilience of these systems. Classical cyber vulnerability assessment approaches rely on the knowledge and experience…

Cryptography and Security · Computer Science 2021-03-18 Christopher Deloglos , Carl Elks , Ashraf Tantawy

Deep neural networks are facing a potential security threat from adversarial examples, inputs that look normal but cause an incorrect classification by the deep neural network. For example, the proposed threat could result in hand-written…

Computer Vision and Pattern Recognition · Computer Science 2016-10-17 Abigail Graese , Andras Rozsa , Terrance E. Boult

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current…

Cryptography and Security · Computer Science 2026-05-12 Monika Jotautaitė , Maria Angelica Martinez , Ollie Matthews , Tyler Tracy

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human…

Computation and Language · Computer Science 2022-02-08 Ethan Perez , Saffron Huang , Francis Song , Trevor Cai , Roman Ring , John Aslanides , Amelia Glaese , Nat McAleese , Geoffrey Irving

Natural language processing (NLP) models have become increasingly popular in real-world applications, such as text classification. However, they are vulnerable to privacy attacks, including data reconstruction attacks that aim to extract…

Computation and Language · Computer Science 2023-06-27 Adel Elmahdy , Ahmed Salem

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…

Computation and Language · Computer Science 2024-05-21 Tom Roth , Inigo Jauregi Unanue , Alsharif Abuadbba , Massimo Piccardi

What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this work, we investigate this question in the setting of high-dimensional binary classification, where…

Machine Learning · Statistics 2025-06-17 Matteo Vilucchio , Lenka Zdeborová , Bruno Loureiro

Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are…

Cryptography and Security · Computer Science 2018-07-25 Kevin Eykholt , Ivan Evtimov , Earlence Fernandes , Bo Li , Dawn Song , Tadayoshi Kohno , Amir Rahmati , Atul Prakash , Florian Tramer

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

Computation and Language · Computer Science 2021-07-27 Jiehang Zeng , Xiaoqing Zheng , Jianhan Xu , Linyang Li , Liping Yuan , Xuanjing Huang

Existing methods for the zero-shot detection of machine-generated text are dominated by three statistical quantities: log-likelihood, log-rank, and entropy. As language models mimic the distribution of human text ever closer, this will…

Computation and Language · Computer Science 2025-03-27 Tom Kempton , Stuart Burrell , Connor Cheverall

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Jindong Gu , Hengshuang Zhao , Volker Tresp , Philip Torr

Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has…

Cryptography and Security · Computer Science 2025-06-10 Zifan Wang , Christina Q. Knight , Jeremy Kritz , Willow E. Primack , Julian Michael

Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this…

Cryptography and Security · Computer Science 2025-10-03 Yinuo Liu , Ruohan Xu , Xilong Wang , Yuqi Jia , Neil Zhenqiang Gong

There are two cases describing how a classifier processes input text, namely, misclassification and correct classification. In terms of misclassified texts, a classifier handles the texts with both incorrect predictions and adversarial…

Computation and Language · Computer Science 2021-10-14 Hoang-Quoc Nguyen-Son , Seira Hidano , Kazuhide Fukushima , Shinsaku Kiyomoto

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…

Computation and Language · Computer Science 2023-09-14 Pavel Burnyshev , Elizaveta Kostenok , Alexey Zaytsev

Data attacks on meter measurements in the power grid can lead to errors in state estimation. This paper presents a new data attack model where an adversary produces changes in state estimation despite failing bad-data detection checks. The…

Cryptography and Security · Computer Science 2015-05-11 Deepjyoti Deka , Ross Baldick , Sriram Vishwanath

Traditional security scanners fail when facing new attack patterns they haven't seen before. They rely on fixed rules and predetermined signatures, making them blind to novel threats. We present a fundamentally different approach: instead…

Cryptography and Security · Computer Science 2025-11-21 Ayush Chaudhary

Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial…

Machine Learning · Computer Science 2020-06-16 Yuanjiang Cao , Xiaocong Chen , Lina Yao , Xianzhi Wang , Wei Emma Zhang