Related papers: Guard: Scalable Straggler Detection and Node Healt…

In this work, we explore the capabilities of multiplexed gradient descent (MGD), a scalable and efficient perturbative zeroth-order training method for estimating the gradient of a loss function in hardware and training it via stochastic…

Unlearning in Large Language Models (LLMs) is crucial for protecting private data and removing harmful knowledge. Most existing approaches rely on fine-tuning to balance unlearning efficiency with general language capabilities. However,…

Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also opens vulnerabilities…

Troubleshooting performance problems of large model training (LMT) is immensely challenging, due to unprecedented scales of modern GPU clusters, the complexity of software-hardware interactions, and the data intensity of the training…

Code generation models are not robust to small perturbations, which often lead to incorrect generations and significantly degrade the performance of these models. Although improving the robustness of code generation models is crucial to…

Although ransomware has received broad attention in media and research, this evolving threat vector still poses a systematic threat. Related literature has explored their detection using various approaches leveraging Machine and Deep…

Graph foundation models have demonstrated remarkable adaptability across diverse downstream tasks through large-scale pretraining on graphs. However, existing implementations of the backbone model, graph transformers, are typically limited…

Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of robustness by causing gradient-based attacks to fail, and they have been broken…

While static analysis is useful in detecting early-stage hardware security bugs, its efficacy is limited because it requires information to form checks and is often unable to explain the security impact of a detected vulnerability. Large…

Network configuration verification enables operators to ensure that the network will behave as intended, prior to deployment of their configurations. Although techniques ranging from graph algorithms to SMT solvers have been proposed,…

Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not…

Monitoring is a runtime verification technique that allows one to check whether an ongoing computation of a system (partial trace) satisfies a given formula. It does not need a complete model of the system, but it typically requires the…

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…

With the vigorous development of artificial intelligence technology, various engineering technology applications have been implemented one after another. The gradient descent method plays an important role in solving various optimization…

The prompt and accurate detection of faults and abnormalities in electric transmission lines is a critical challenge in smart grid systems. Existing methods mostly rely on model-based approaches, which may not capture all the aspects of…

As modern systems increasingly rely on GPUs for computationally intensive tasks such as machine learning acceleration, ensuring the integrity of GPU computation has become critically important. Recent studies have shown that GPU kernels are…

Multitask learning is a widely used paradigm for training models on diverse tasks, with applications ranging from graph neural networks to language model fine-tuning. Since tasks may interfere with each other, a key notion for modeling…

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

Computational cytology faces two major challenges: i) instance-level labels are unreliable and prohibitively costly to obtain, ii) witness rates are extremely low. We propose SLAM-AGS, a Slide-Label-Aware Multitask pretraining framework…