相关论文: Bad Citrus: Reducing Adversarial Costs with Model …

Machine Learning (ML) models are applied in a variety of tasks such as network intrusion detection or Malware classification. Yet, these models are vulnerable to a class of malicious inputs known as adversarial examples. These are slightly…

Transformer-based language models for code have shown remarkable performance in various software analytics tasks, but their adoption is hindered by high computational costs, slow inference speeds, and substantial environmental impact. Model…

We propose a new simulation-based estimation method, adversarial estimation, for structural models. The estimator is formulated as the solution to a minimax problem between a generator (which generates simulated observations using the…

Deep neural networks are vulnerable to adversarial examples, posing a threat to the models' applications and raising security concerns. An intriguing property of adversarial examples is their strong transferability. Several methods have…

As frontier AIs become more powerful and costly to develop, adversaries have increasing incentives to steal model weights by mounting exfiltration attacks. In this work, we consider exfiltration attacks where an adversary attempts to sneak…

As machine learning algorithms continue to improve, there is an increasing need for explaining why a model produces a certain prediction for a certain input. In recent years, several methods for model interpretability have been developed,…

Despite numerous attempts to defend deep learning based image classifiers, they remain susceptible to the adversarial attacks. This paper proposes a technique to identify susceptible classes, those classes that are more easily subverted. To…

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…

Adversarial training has been widely studied in recent years due to its role in improving model robustness against adversarial attacks. This paper focuses on comparing different distributed adversarial training algorithms--including…

Adversarial face examples possess two critical properties: Visual Quality and Transferability. However, existing approaches rarely address these properties simultaneously, leading to subpar results. To address this issue, we propose a novel…

We study adversarial examples in a black-box setting where the adversary only has API access to the target model and each query is expensive. Prior work on black-box adversarial examples follows one of two main strategies: (1) transfer…

We study Label-Smoothing as a means for improving adversarial robustness of supervised deep-learning models. After establishing a thorough and unified framework, we propose several variations to this general method: adversarial, Boltzmann…

We study the problem of aligning the supports of distributions. Compared to the existing work on distribution alignment, support alignment does not require the densities to be matched. We propose symmetric support difference as a divergence…

Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an…

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…

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…

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better…

We consider adversarial attacks to a black-box model when no queries are allowed. In this setting, many methods directly attack surrogate models and transfer the obtained adversarial examples to fool the target model. Plenty of previous…

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate…

Network pruning has been known to produce compact models without much accuracy degradation. However, how the pruning process affects a network's robustness and the working mechanism behind remain unresolved. In this work, we theoretically…