相关论文: Adversarial Decoding: Generating Readable Document…

Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode…

Retrieval-augmented generation (RAG) systems can effectively mitigate the hallucination problem of large language models (LLMs),but they also possess inherent vulnerabilities. Identifying these weaknesses before the large-scale real-world…

In malware behavioral analysis, the list of accessed and created files very often indicates whether the examined file is malicious or benign. However, malware authors are trying to avoid detection by generating random filenames and/or…

Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are…

Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs against certain criteria (e.g.,…

In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but its openness introduces vulnerabilities that can be exploited by poisoning attacks. Existing poisoning methods for RAG…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Adversarial examples have recently proven to be able to fool deep learning methods by adding carefully crafted small perturbation to the input space image. In this paper, we study the possibility of generating adversarial examples for…

Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer…

Documents often exhibit various forms of degradation, which make it hard to be read and substantially deteriorate the performance of an OCR system. In this paper, we propose an effective end-to-end framework named Document Enhancement…

The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body…

Automated adversary emulation is becoming an indispensable tool of network security operators in testing and evaluating their cyber defenses. At the same time, it has exposed how quickly adversaries can propagate through the network. While…

Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack the model on each sample independently. Instead of…

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…

Over the past decade, side-channels have proven to be significant and practical threats to modern computing systems. Recent attacks have all exploited the underlying shared hardware. While practical, mounting such a complicated attack is…