Related papers: Versatile Weight Attack via Flipping Limited Bits

The rapid adoption of large language models (LLMs) in critical domains has spurred extensive research into their security issues. While input manipulation attacks (e.g., prompt injection) have been well studied, Bit-Flip Attacks (BFAs) --…

Spiking neural networks (SNNs) that enable low-power design on edge devices have recently attracted significant research. However, the temporal characteristic of SNNs causes high latency, high bandwidth and high energy consumption for the…

Similar to the revolution of open source code sharing, Artificial Intelligence (AI) model sharing is gaining increased popularity. However, the fast adaptation in the industry, lack of awareness, and ability to exploit the models make them…

Federated Learning (FL) is a distributed learning paradigm that enables different parties to train a model together for high quality and strong privacy protection. In this scenario, individual participants may get compromised and perform…

Malicious attackers can generate targeted adversarial examples by imposing tiny noises, forcing neural networks to produce specific incorrect outputs. With cross-model transferability, network models remain vulnerable even in black-box…

Fault injection attacks are a potent threat against embedded implementations of neural network models. Several attack vectors have been proposed, such as misclassification, model extraction, and trojan/backdoor planting. Most of these…

State-space models (SSMs), exemplified by the Mamba architecture, have recently emerged as state-of-the-art sequence-modeling frameworks, offering linear-time scalability together with strong performance in long-context settings. Owing to…

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Deep neural networks are vulnerable to adversarial examples that mislead models with imperceptible perturbations. In audio, although adversarial examples have achieved incredible attack success rates on white-box settings and black-box…

Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack…

This work introduces a framework to address the computational complexity inherent in Mixed-Integer Programming (MIP) models by harnessing the potential of deep learning. By employing deep learning, we construct problem-specific heuristics…

Prior attacks on graph neural networks have mostly focused on graph poisoning and evasion, neglecting the network's weights and biases. Traditional weight-based fault injection attacks, such as bit flip attacks used for convolutional neural…

Adversarial Training (AT) effectively improves the robustness of Deep Neural Networks (DNNs) to adversarial attacks. Generally, AT involves training DNN models with adversarial examples obtained within a pre-defined, fixed perturbation…

State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to adversarial manipulation and backdoor attacks. Backdoored models deviate from expected behavior on inputs with predefined triggers while retaining performance…

Audio-based machine learning systems frequently use public or third-party data, which might be inaccurate. This exposes deep neural network (DNN) models trained on such data to potential data poisoning attacks. In this type of assault,…

Meta-learning methods aim to build learning algorithms capable of quickly adapting to new tasks in low-data regime. One of the most difficult benchmarks of such algorithms is a one-shot learning problem. In this setting many algorithms face…

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples,…

We investigate the role of transferability of adversarial attacks in the observed vulnerabilities of Deep Neural Networks (DNNs). We demonstrate that introducing randomness to the DNN models is sufficient to defeat adversarial attacks,…

Despite their impressive performance, deep neural networks (DNNs) are widely known to be vulnerable to adversarial attacks, which makes it challenging for them to be deployed in security-sensitive applications, such as autonomous driving.…

The transferability of adversarial examples poses a significant security challenge for deep neural networks, which can be attacked without knowing anything about them. In this paper, we propose a new Segmented Gaussian Pyramid (SGP) attack…