相关论文: Bullseye Polytope: A Scalable Clean-Label Poisonin…

Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case attacks that target a small fraction of the input space are nearly impossible to detect using existing…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation. These attacks pose great threats to the applications of…

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Machine learning (ML) malware detectors rely heavily on crowd-sourced AntiVirus (AV) labels, with platforms like VirusTotal serving as a trusted source of malware annotations. But what if attackers could manipulate these labels to classify…

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

Semi-supervised Federated Learning (SSFL) has recently drawn much attention due to its practical consideration, i.e., the clients may only have unlabeled data. In practice, these SSFL systems implement semi-supervised training by assigning…

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible, reliance on third-party or internet data is common. Recent studies show CL models are vulnerable…

Code autocompletion is an integral feature of modern code editors and IDEs. The latest generation of autocompleters uses neural language models, trained on public open-source code repositories, to suggest likely (not just statically…

Recommender Systems~(RS) have been shown to be vulnerable to injective attacks, where attackers inject limited fake user profiles to promote the exposure of target items to real users for unethical gains (e.g., economic or political…

The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attention. In this paper, we improve the transferability of…

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out. We achieve this by modifying subliminal…

Model adaptation tackles the distribution shift problem with a pre-trained model instead of raw data, which has become a popular paradigm due to its great privacy protection. Existing methods always assume adapting to a clean target domain,…

Training-data poisoning attacks can induce targeted, undetectable failure in deep neural networks by corrupting a vanishingly small fraction of training labels. We demonstrate this on acoustic vehicle classification using the MELAUDIS urban…

Semi-supervised machine learning (SSL) is gaining popularity as it reduces the cost of training ML models. It does so by using very small amounts of (expensive, well-inspected) labeled data and large amounts of (cheap, non-inspected)…

Predicitions made by neural networks can be fraudulently altered by so-called poisoning attacks. A special case are backdoor poisoning attacks. We study suitable detection methods and introduce a new method called Heatmap Clustering. There,…

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

The transferability of adversarial examples across deep neural networks (DNNs) is the crux of many black-box attacks. Many prior efforts have been devoted to improving the transferability via increasing the diversity in inputs of some…