Related papers: Intrinsic Certified Robustness of Bagging against …

Deep learning models have gained popularity for conducting various tasks involving source code. However, their black-box nature raises concerns about potential risks. One such risk is a poisoning attack, where an attacker intentionally…

Poisoning-based backdoor attacks expose vulnerabilities in the data preparation stage of deep neural network (DNN) training. The DNNs trained on the poisoned dataset will be embedded with a backdoor, making them behave well on clean data…

Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…

We give a formal verification procedure that decides whether a classifier ensemble is robust against arbitrary randomized attacks. Such attacks consist of a set of deterministic attacks and a distribution over this set. The…

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

We introduce a novel clean-label targeted poisoning attack on learning mechanisms. While classical poisoning attacks typically corrupt data via addition, modification and omission, our attack focuses on data omission only. Our attack…

In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing…

Behavior Cloning (BC) is a popular framework for training sequential decision policies from expert demonstrations via supervised learning. As these policies are increasingly being deployed in the real world, their robustness and potential…

We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time, this trigger causes the classifier to predict some target…

As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and generation. However, these systems remain susceptible to malicious prompts that induce unsafe or policy-violating…

Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification techniques for verifying neural network properties. While…

An ensemble consists of a set of individually trained classifiers (such as neural networks or decision trees) whose predictions are combined when classifying novel instances. Previous research has shown that an ensemble is often more…

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

Deep learning is a standard tool in the field of high-energy physics, facilitating considerable sensitivity enhancements for numerous analysis strategies. In particular, in identification of physics objects, such as jet flavor tagging,…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Modern machine learning models are sensitive to the manipulation of both the training data (poisoning attacks) and inference data (adversarial examples). Recognizing this issue, the community has developed many empirical defenses against…

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…

Deep neural networks have proven to be extremely powerful, however, they are also vulnerable to adversarial attacks which can cause hazardous incorrect predictions in safety-critical applications. Certified robustness via randomized…

Most recent studies have shown several vulnerabilities to attacks with the potential to jeopardize the integrity of the model, opening in a few recent years a new window of opportunity in terms of cyber-security. The main interest of this…