Related papers: Automated Discovery of Adaptive Attacks on Adversa…
Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we investigate an attack-agnostic defense against adversarial attacks on…
Class incremental learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, it has been shown that such approaches are…
Defending against physical adversarial attacks is a rapidly growing topic in deep learning and computer vision. Prominent forms of physical adversarial attacks, such as overlaid adversarial patches and objects, share similarities with…
This work proposes a procedure for designing algorithms for specific adaptive data collection tasks like active learning and pure-exploration multi-armed bandits. Unlike the design of traditional adaptive algorithms that rely on…
We introduce a defense against adversarial attacks on LLMs utilizing self-evaluation. Our method requires no model fine-tuning, instead using pre-trained models to evaluate the inputs and outputs of a generator model, significantly reducing…
Although deep neural networks have shown promising performances on various tasks, they are susceptible to incorrect predictions induced by imperceptibly small perturbations in inputs. A large number of previous works proposed to detect…
Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is valuable, there has…
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…
This note documents an implementation issue in recent adaptive attacks (Zhang et al. [2024]) against the multi-resolution self-ensemble defense (Fort and Lakshminarayanan [2024]). The implementation allowed adversarial perturbations to…
Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density…
This work conducts the first analysis on the robustness against adversarial attacks on self-supervised Vision Transformers trained using DINO. First, we evaluate whether features learned through self-supervision are more robust to…
Trajectory prediction is critical for the safe planning and navigation of automated vehicles. The trajectory prediction models based on the neural networks are vulnerable to adversarial attacks. Previous attack methods have achieved high…
Autonomous vehicles must be comprehensively evaluated before deployed in cities and highways. However, most existing evaluation approaches for autonomous vehicles are static and lack adaptability, so they are usually inefficient in…
Learning models capable of providing reliable predictions in the face of adversarial actions has become a central focus of the machine learning community in recent years. This challenge arises from observing that data encountered at…
Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defense strategies, adversarial training aims to promote the robustness of models intrinsically.…
Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defenses include Barrage of…
How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions,…
The forecast of electrical loads is essential for the planning and operation of the power system. Recently, advances in deep learning have enabled more accurate forecasts. However, deep neural networks are prone to adversarial attacks.…
Deep reinforcement learning (DRL) has emerged as a promising paradigm for autonomous driving. However, despite their advanced capabilities, DRL-based policies remain highly vulnerable to adversarial attacks, posing serious safety risks in…
Autonomous cars are well known for being vulnerable to adversarial attacks that can compromise the safety of the car and pose danger to other road users. To effectively defend against adversaries, it is required to not only test autonomous…