Related papers: Architectural Backdoors for Within-Batch Data Stea…

Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…

In big data systems, the infrastructure is such that large amounts of data are hosted away from the users. In such a system information security is considered as a major challenge. From a customer perspective, one of the big risks in…

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

Machine learning models are routinely deployed on a wide range of computing hardware. Although such hardware is typically expected to produce identical results, differences in its design can lead to small numerical variations during…

We investigate a new threat to neural sequence-to-sequence (seq2seq) models: training-time attacks that cause models to "spin" their output and support a certain sentiment when the input contains adversary-chosen trigger words. For example,…

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger, while it…

Deep Generative Models (DGMs) are a popular class of deep learning models which find widespread use because of their ability to synthesize data from complex, high-dimensional manifolds. However, even with their increasing industrial…

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Together with impressive advances touching every aspect of our society, AI technology based on Deep Neural Networks (DNN) is bringing increasing security concerns. While attacks operating at test time have monopolised the initial attention…

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

As society grows more reliant on machine learning, ensuring the security of machine learning systems against sophisticated attacks becomes a pressing concern. A recent result of Goldwasser, Kim, Vaikuntanathan, and Zamir (2022) shows that…

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently,…

Link prediction, inferring the undiscovered or potential links of the graph, is widely applied in the real-world. By facilitating labeled links of the graph as the training data, numerous deep learning based link prediction methods have…

Backdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker.…

Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (XAI). Among these efforts, Concept Bottleneck Models (CBMs)…

Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove them. These defences work by…

DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…

The foundation models (FMs) have been used to generate synthetic public datasets for the heterogeneous federated learning (HFL) problem where each client uses a unique model architecture. However, the vulnerabilities of integrating FMs,…

Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-specific data for code-related downstream tasks, thereby limiting…

Dataset Condensation (DC) is a data-efficient learning paradigm that synthesizes small yet informative datasets, enabling models to match the performance of full-data training. However, recent work exposes a critical vulnerability of DC to…