Related papers: Rounding-Guided Backdoor Injection in Deep Learnin…

In recent years, a CRA (Credit Risk Analysis) quantum algorithm with a quadratic speedup over classical analogous methods has been introduced. We propose a new variant of this quantum algorithm with the intent of overcoming some of the most…

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications.…

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASE, a novel method that can erase the…

Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural…

Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usually requires access to the original training data to…

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory…

Back-door attack poses a severe threat to deep learning systems. It injects hidden malicious behaviors to a model such that any input stamped with a special pattern can trigger such behaviors. Detecting back-door is hence of pressing need.…

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Simulated environments are a key piece in the success of Reinforcement Learning (RL), allowing practitioners and researchers to train decision making agents without running expensive experiments on real hardware. Simulators remain a…

Ramp metering is the act of controlling on-going vehicles to the highway mainlines. Decades of practices of ramp metering have proved that ramp metering can decrease total travel time, mitigate shockwaves, decrease rear-end collisions by…

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…

Large Language Model (LLM) unlearning aims to remove targeted knowledge from a trained model, but practical deployments often require post-training quantization (PTQ) for efficient inference. However, aggressive low-bit PTQ can mask…

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

As artificial intelligence becomes more prevalent in our lives, people are enjoying the convenience it brings, but they are also facing hidden threats, such as data poisoning and adversarial attacks. These threats can have disastrous…

Deep anomaly detection on sequential data has garnered significant attention due to the wide application scenarios. However, deep learning-based models face a critical security threat - their vulnerability to backdoor attacks. In this…

Federated learning (FL) enables multiple clients to collaboratively train models without sharing their local data, and becomes an important privacy-preserving machine learning framework. However, classical FL faces serious security and…

Quantum Machine Learning (QML) amalgamates quantum computing paradigms with machine learning models, providing significant prospects for solving complex problems. However, with the expansion of numerous third-party vendors in the Noisy…