相关论文: BAGM: A Backdoor Attack for Manipulating Text-to-I…

When a small number of poisoned samples are injected into the training dataset of a deep neural network, the network can be induced to exhibit malicious behavior during inferences, which poses potential threats to real-world applications.…

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,…

While text-to-image diffusion models demonstrate impressive generation capabilities, they also exhibit vulnerability to backdoor attacks, which involve the manipulation of model outputs through malicious triggers. In this paper, for the…

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

In recent years, machine learning models have been shown to be vulnerable to backdoor attacks. Under such attacks, an adversary embeds a stealthy backdoor into the trained model such that the compromised models will behave normally on clean…

Graphical User Interface (GUI) agents powered by Large Vision-Language Models (LVLMs) have emerged as a revolutionary approach to automating human-machine interactions, capable of autonomously operating personal devices (e.g., mobile…

Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While model editing has been proposed to remove or filter…

Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent…

Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many generative AI applications, such as text-to-image…

In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first,…

In recent years, text-to-image (T2I) diffusion models have gained significant attention for their ability to generate high quality images reflecting text prompts. However, their growing popularity has also led to the emergence of backdoor…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

The tremendous recent advances in generative artificial intelligence techniques have led to significant successes and promise in a wide range of different applications ranging from conversational agents and textual content generation to…

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…

Generative Artificial Intelligence (AI) has created unprecedented opportunities for creative expression, education, and research. Text-to-image systems such as DALL.E, Stable Diffusion, and Midjourney can now convert ideas into visuals…

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional context modeling. Yet their security implications,…

With the growing popularity of Large Language Models (LLMs) and vector databases, private textual data is increasingly processed and stored as numerical embeddings. However, recent studies have proven that such embeddings are vulnerable to…

Deep neural networks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to the target…