Backdoor attacks are serious security threats to machine learning models where an adversary can inject poisoned samples into the training set, causing a backdoored model which predicts poisoned samples with particular triggers to particular target classes, while behaving normally on benign samples. In this paper, we explore the task of purifying a backdoored model using a small clean dataset. By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk, which mainly captures the risk on the shared adversarial examples (SAEs) between the backdoored model and the purified model. This upper bound further suggests a novel bi-level optimization problem for mitigating backdoor using adversarial training techniques. To solve it, we propose Shared Adversarial Unlearning (SAU). Specifically, SAU first generates SAEs, and then, unlearns the generated SAEs such that they are either correctly classified by the purified model and/or differently classified by the two models, such that the backdoor effect in the backdoored model will be mitigated in the purified model. Experiments on various benchmark datasets and network architectures show that our proposed method achieves state-of-the-art performance for backdoor defense.

Backdoor attacks are serious security threats to machine learning models where an adversary can inject poisoned samples into the training set, causing a backdoored model which predicts poisoned samples with particular triggers to particular target classes, while behaving normally on benign samples. In this paper, we explore the task of purifying a backdoored model using a small clean dataset. By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk, which mainly captures the risk on the shared adversarial examples (SAEs) between the backdoored model and the purified model. This upper bound further suggests a novel bi-level optimization problem for mitigating backdoor using adversarial training techniques. To solve it, we propose Shared Adversarial Unlearning (SAU).

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to their effectiveness, also renders them susceptible to adversarial attacks. Among these, backdoor attacks are especially concerning, as they involve surreptitiously embedding specific triggers within training data, causing the model to exhibit aberrant behavior when presented with input containing the triggers. Such attacks often exploit vulnerabilities in outsourced processes, compromising model integrity without affecting performance on clean (trigger-free) input data. In this paper, we present a comprehensive review of existing mitigation strategies designed to counter backdoor attacks in image recognition. We provide an in-depth analysis of the theoretical foundations, practical efficacy, and limitations of these approaches. In addition, we conduct an extensive benchmarking of sixteen state-of-the-art approaches against eight distinct backdoor attacks, utilizing three datasets, four model architectures, and three poisoning ratios. Our results, derived from 122,236 individual experiments, indicate that while many approaches provide some level of protection, their performance can vary considerably. Furthermore, when compared to two seminal approaches, most newer approaches do not demonstrate substantial improvements in overall performance or consistency across diverse settings. Drawing from these findings, we propose potential directions for developing more effective and generalizable defensive mechanisms in the future.

As society grows more reliant on machine learning, ensuring the security of machine learning systems against sophisticated attacks becomes a pressing concern. A recent result of Goldwasser, Kim, Vaikuntanathan, and Zamir (2022) shows that an adversary can plant undetectable backdoors in machine learning models, allowing the adversary to covertly control the model's behavior. Backdoors can be planted in such a way that the backdoored machine learning model is computationally indistinguishable from an honest model without backdoors. In this paper, we present strategies for defending against backdoors in ML models, even if they are undetectable. The key observation is that it is sometimes possible to provably mitigate or even remove backdoors without needing to detect them, using techniques inspired by the notion of random self-reducibility. This depends on properties of the ground-truth labels (chosen by nature), and not of the proposed ML model (which may be chosen by an attacker). We give formal definitions for secure backdoor mitigation, and proceed to show two types of results. First, we show a "global mitigation" technique, which removes all backdoors from a machine learning model under the assumption that the ground-truth labels are close to a Fourier-heavy function. Second, we consider distributions where the ground-truth labels are close to a linear or polynomial function in $\mathbb{R}^n$. Here, we show "local mitigation" techniques, which remove backdoors with high probability for every inputs of interest, and are computationally cheaper than global mitigation. All of our constructions are black-box, so our techniques work without needing access to the model's representation (i.e., its code or parameters). Along the way we prove a simple result for robust mean estimation.

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research reveals that backdoors can be erased from infected DNNs by pruning a specific group of neurons, while how to effectively identify and remove these backdoor-associated neurons remains an open challenge. Most of the existing defense methods rely on defined rules and focus on neuron's local properties, ignoring the exploration and optimization of pruning policies. To address this gap, we propose an Optimized Neuron Pruning (ONP) method combined with Graph Neural Network (GNN) and Reinforcement Learning (RL) to repair backdoor models. Specifically, ONP first models the target DNN as graphs based on neuron connectivity, and then uses GNN-based RL agents to learn graph embeddings and find a suitable pruning policy. To the best of our knowledge, this is the first attempt to employ GNN and RL for optimizing pruning policies in the field of backdoor defense. Experiments show, with a small amount of clean data, ONP can effectively prune the backdoor neurons implanted by a set of backdoor attacks at the cost of negligible performance degradation, achieving a new state-of-the-art performance for backdoor mitigation.

Deep Neural Networks (DNN) are becoming increasingly more important in assisted and automated driving. Using such entities which are obtained using machine learning is inevitable: tasks such as recognizing traffic signs cannot be developed reasonably using traditional software development methods. DNN however do have the problem that they are mostly black boxes and therefore hard to understand and debug. One particular problem is that they are prone to hidden backdoors. This means that the DNN misclassifies its input, because it considers properties that should not be decisive for the output. Backdoors may either be introduced by malicious attackers or by inappropriate training. In any case, detecting and removing them is important in the automotive area, as they might lead to safety violations with potentially severe consequences. In this paper, we introduce a novel method to remove backdoors. Our method works for both intentional as well as unintentional backdoors. We also do not require prior knowledge about the shape or distribution of backdoors. Experimental evidence shows that our method performs well on several medium-sized examples.