Related papers: SCOUT: A Defense Against Data Poisoning Attacks in…
In recent years, the adoption of cloud services has been expanding at an unprecedented rate. As more and more organizations migrate or deploy their businesses to the cloud, a multitude of related cybersecurity incidents such as data…
Dense retrieval systems have been widely used in various NLP applications. However, their vulnerabilities to potential attacks have been underexplored. This paper investigates a novel attack scenario where the attackers aim to mislead the…
Speaker identification (SI) determines a speaker's identity based on their spoken utterances. Previous work indicates that SI deep neural networks (DNNs) are vulnerable to backdoor attacks. Backdoor attacks involve embedding hidden triggers…
Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…
Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…
Recent advances in natural language processing and the increased use of large language models have exposed new security vulnerabilities, such as backdoor attacks. Previous backdoor attacks require input manipulation after model distribution…
Backdoor attacks pose an important security threat to textual large language models. Exploring textual backdoor attacks not only helps reveal the potential security risks of models, but also promotes innovation and development of defense…
Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered at inference. Existing backdoor attack methods typically…
As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…
Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…
Large language models play a crucial role in modern natural language processing technologies. However, their extensive use also introduces potential security risks, such as the possibility of black-box attacks. These attacks can embed…
Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs.…
Deep neural networks (DNNs) are vulnerable to a class of attacks called "backdoor attacks", which create an association between a backdoor trigger and a target label the attacker is interested in exploiting. A backdoored DNN performs well…
Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most…
Backdoor attacks have been considered a severe security threat to deep learning. Such attacks can make models perform abnormally on inputs with predefined triggers and still retain state-of-the-art performance on clean data. While backdoor…
The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…
Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to…
We investigate a new threat to neural sequence-to-sequence (seq2seq) models: training-time attacks that cause models to "spin" their outputs so as to support an adversary-chosen sentiment or point of view -- but only when the input contains…
As a novel privacy-preserving paradigm aimed at reducing client computational costs and achieving data utility, split learning has garnered extensive attention and proliferated widespread applications across various fields, including smart…
We demonstrate how publicly available social-media data and generative AI (GenAI) can be misused to automate and scale highly personalized, context-aware spear-phishing campaigns. With minimal attacker effort, a small amount of public…