相关论文: Attacks Meet Interpretability (AmI) Evaluation and…

Deep learning methods have gained increased attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper use of data artifacts and the accurate problem formulation of…

We propose a probabilistic perspective on adversarial examples, allowing us to embed subjective understanding of semantics as a distribution into the process of generating adversarial examples, in a principled manner. Despite significant…

Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the…

Adversarial examples have attracted significant attention over the years, yet understanding their frequency-based characteristics remains insufficient. In this paper, we investigate the intriguing properties of adversarial examples in the…

Exploiting social media to spread hate has tremendously increased over the years. Lately, multi-modal hateful content such as memes has drawn relatively more traction than uni-modal content. Moreover, the availability of implicit content…

Nowadays, numerous applications incorporate machine learning (ML) algorithms due to their prominent achievements. However, many studies in the field of computer vision have shown that ML can be fooled by intentionally crafted instances,…

Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally…

Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic…

In this paper, we investigate the impact of adversarial attacks on the explainability of deep learning models, which are commonly criticized for their black-box nature despite their capacity for autonomous feature extraction. This black-box…

Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works…

Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpretation, that explains the model's decision process on that…

Adversarial attack perturbs an image with an imperceptible noise, leading to incorrect model prediction. Recently, a few works showed inherent bias associated with such attack (robustness bias), where certain subgroups in a dataset (e.g.…

Adversarial examples are a type of attack on machine learning (ML) systems which cause misclassification of inputs. Achieving robustness against adversarial examples is crucial to apply ML in the real world. While most prior work on…

Despite the tremendous success of neural networks, benign images can be corrupted by adversarial perturbations to deceive these models. Intriguingly, images differ in their attackability. Specifically, given an attack configuration, some…

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Adversarial examples are of wide concern due to their impact on the reliability of contemporary machine learning systems. Effective adversarial examples are mostly found via white-box attacks. However, in some cases they can be transferred…

Deep learning techniques have achieved superior performance in computer-aided medical image analysis, yet they are still vulnerable to imperceptible adversarial attacks, resulting in potential misdiagnosis in clinical practice. Oppositely,…

In the era of widespread public use of AI systems across various domains, ensuring adversarial robustness has become increasingly vital to maintain safety and prevent undesirable errors. Researchers have curated various adversarial datasets…

It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. Applying mixup in training provides an effective mechanism to…

In this article I describe a research agenda for securing machine learning models against adversarial inputs at test time. This article does not present results but instead shares some of my thoughts about where I think that the field needs…