Related papers: Supporting Secured Integration of Microarchitectur…

Machine learning-based malware detectors are increasingly vulnerable to adversarial examples. Traditional defenses, such as one-shot adversarial training, often fail against adaptive attackers who use reinforcement learning to bypass…

Model merging (MM) recently emerged as an effective method for combining large deep learning models. However, it poses significant security risks. Recent research shows that it is highly susceptible to backdoor attacks, which introduce a…

Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D points, audio, text, etc. Similar to unimodal models, many…

The vulnerability of machine learning systems to adversarial attacks questions their usage in many applications. In this paper, we propose a randomized diversification as a defense strategy. We introduce a multi-channel architecture in a…

Over the years, most research towards defenses against adversarial attacks on machine learning models has been in the image recognition domain. The ML-based malware detection domain has received less attention despite its importance.…

Rigorous quantitative evaluation of microarchitectural side channels is challenging for two reasons. First, the processors, attacks, and defenses often exhibit probabilistic behaviors. These probabilistic behaviors arise due to natural…

Microservice architectures (MSA) are becoming trending alternatives to existing software development paradigms notably for developing complex and distributed applications. Microservices emerged as an architectural design pattern aiming to…

Fault injection attacks represent an effective threat to embedded systems. Recently, Laurent et al. have reported that fault injection attacks can leverage faults inside the microarchitecture. However, state-of-the-art counter-measures,…

Side-channel attacks have become a severe threat to the confidentiality of computer applications and systems. One popular type of such attacks is the microarchitectural attack, where the adversary exploits the hardware features to break the…

Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose…

Model merging has gained significant attention as a cost-effective approach to integrate multiple single-task fine-tuned models into a unified one that can perform well on multiple tasks. However, existing model merging techniques primarily…

Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive learning, MIM attains state-of-the-art performance by masking…

We formulate and analyze a simplest Markov decision process model for intrusion tolerance problems, assuming that (i) each attack proceeds through one or more steps before the system's security fails, (ii) defensive responses that target…

Multi-armed adversarial attacks, in which multiple algorithms and objective loss functions are simultaneously used at evaluation time, have been shown to be highly successful in fooling state-of-the-art adversarial examples detectors while…

With the growing amount of cyber threats, the need for development of high-assurance cyber systems is becoming increasingly important. The objective of this paper is to address the challenges of modeling and detecting sophisticated network…

Multimodal foundation models (MFMs) integrate diverse data modalities to support complex and wide-ranging tasks. However, this integration also introduces distinct safety and security challenges. In this paper, we unify the concepts of…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

With the continuous improvement of attack methods, there are more and more distributed, complex, targeted attacks in which the attackers use combined attack methods to achieve the purpose. Advanced cyber attacks include multiple stages to…

Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting,…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…