English
Related papers

Related papers: Don't sweat the small stuff, classify the rest: Sa…

200 papers

Support Vector Machines (SVMs) are vulnerable to targeted training data manipulations such as poisoning attacks and label flips. By carefully manipulating a subset of training samples, the attacker forces the learner to compute an incorrect…

Machine Learning · Computer Science 2020-08-24 Sandamal Weerasinghe , Tansu Alpcan , Sarah M. Erfani , Christopher Leckie

Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model jailbreaks. In this work, we analyze how CLIP vision encoders…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Lorenz Hufe , Constantin Venhoff , Erblina Purelku , Maximilian Dreyer , Sebastian Lapuschkin , Wojciech Samek

Federated Learning(FL), in theory, preserves privacy of individual clients' data while producing quality machine learning models. However, attacks such as Deep Leakage from Gradients(DLG) severely question the practicality of FL. In this…

Machine Learning · Computer Science 2024-08-19 Joon Kim , Sejin Park

In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Safe RL, where an agent…

Machine Learning · Statistics 2025-03-26 Edwin Hamel-De le Court , Francesco Belardinelli , Alexander W. Goodall

Large language models (LLMs) are highly sensitive to even small amounts of unsafe training data, making effective detection and filtering essential for trustworthy model development. Current state-of-the-art (SOTA) detection approaches…

Machine Learning · Computer Science 2025-10-13 Yijun Pan , Taiwei Shi , Jieyu Zhao , Jiaqi W. Ma

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Computation and Language · Computer Science 2025-10-27 Bushra Sabir , Yansong Gao , Alsharif Abuadbba , M. Ali Babar

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While…

Computation and Language · Computer Science 2023-07-13 Yahan Yang , Soham Dan , Dan Roth , Insup Lee

Few-shot text classification aims to recognize unseen classes with limited labeled text samples. Existing approaches focus on boosting meta-learners by developing complex algorithms in the training stage. However, the labeled samples are…

Machine Learning · Computer Science 2026-03-04 Yunlong Gao , Xinyue Liu , Yingbo Wang , Linlin Zong , Bo Xu

Text-to-image models are vulnerable to the stepwise "Divide-and-Conquer Attack" (DACA) that utilize a large language model to obfuscate inappropriate content in prompts by wrapping sensitive text in a benign narrative. To mitigate stepwise…

Cryptography and Security · Computer Science 2024-12-18 Portia Cooper , Harshita Narnoli , Mihai Surdeanu

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Machine Learning · Computer Science 2020-10-14 Ruoxin Chen , Jie Li , Chentao Wu , Bin Sheng , Ping Li

With the growth of adversarial attacks against machine learning models, several concerns have emerged about potential vulnerabilities in designing deep neural network-based intrusion detection systems (IDS). In this paper, we study the…

Machine Learning · Computer Science 2019-11-01 Rana Abou Khamis , Omair Shafiq , Ashraf Matrawy

Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters. Few try to attack classifiers by rewriting a whole sentence, due to the…

Computation and Language · Computer Science 2022-10-21 Lei Xu , Ivan Ramirez , Kalyan Veeramachaneni

As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to eliminating the need for labeled data, research has found…

Cryptography and Security · Computer Science 2023-08-15 Changjiang Li , Ren Pang , Zhaohan Xi , Tianyu Du , Shouling Ji , Yuan Yao , Ting Wang

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…

Machine Learning · Computer Science 2020-01-13 Hadi Salman , Greg Yang , Jerry Li , Pengchuan Zhang , Huan Zhang , Ilya Razenshteyn , Sebastien Bubeck

Federated Learning (FL) is a novel client-server distributed learning framework that can protect data privacy. However, recent works show that FL is vulnerable to poisoning attacks. Many defenses with robust aggregators (AGRs) are proposed…

Cryptography and Security · Computer Science 2024-07-26 Yuxin Yang , Qiang Li , Chenfei Nie , Yuan Hong , Meng Pang , Binghui Wang

As large language models increasingly memorize web-scraped training content, they risk exposing copyrighted or private information. Existing protections require compliance from crawlers or model developers, fundamentally limiting their…

Cryptography and Security · Computer Science 2025-12-17 Ruixuan Liu , Toan Tran , Tianhao Wang , Hongsheng Hu , Shuo Wang , Li Xiong

Neural models enjoy widespread use across a variety of tasks and have grown to become crucial components of many industrial systems. Despite their effectiveness and extensive popularity, they are not without their exploitable flaws.…

Sound · Computer Science 2019-02-26 Krishan Rajaratnam , Jugal Kalita

Randomized smoothing is a recent and celebrated solution to certify the robustness of any classifier. While it indeed provides a theoretical robustness against adversarial attacks, the dimensionality of current classifiers necessarily…

Cryptography and Security · Computer Science 2022-05-02 Thibault Maho , Teddy Furon , Erwan Le Merrer

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such…

Machine Learning · Statistics 2019-11-19 Sanjay Kariyappa , Moinuddin K Qureshi

Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input $x$ and any target classification $t$, it is possible to find a new…

Cryptography and Security · Computer Science 2017-03-23 Nicholas Carlini , David Wagner