相关论文: PETGEN: Personalized Text Generation Attack on Dee…

Text-to-image diffusion models are pushing the boundaries of what generative AI can achieve in our lives. Beyond their ability to generate general images, new personalization techniques have been proposed to customize the pre-trained base…

Evaluating the risk level of adversarial images is essential for safely deploying face authentication models in the real world. Popular approaches for physical-world attacks, such as print or replay attacks, suffer from some limitations,…

Can machine learning models for recommendation be easily fooled? While the question has been answered for hand-engineered fake user profiles, it has not been explored for machine learned adversarial attacks. This paper attempts to close…

Healthcare predictive analytics aids medical decision-making, diagnosis prediction and drug review analysis. Therefore, prediction accuracy is an important criteria which also necessitates robust predictive language models. However, the…

Sequence-based deep learning models (e.g., RNNs), can detect malware by analyzing its behavioral sequences. Meanwhile, these models are susceptible to adversarial attacks. Attackers can create adversarial samples that alter the sequence…

Comment generation, a new and challenging task in Natural Language Generation (NLG), attracts a lot of attention in recent years. However, comments generated by previous work tend to lack pertinence and diversity. In this paper, we propose…

In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases,…

Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several…

Recently, many profiling side-channel attacks based on Machine Learning and Deep Learning have been proposed. Most of them focus on reducing the number of traces required for successful attacks by optimizing the modeling algorithms. In…

Natural Language Inference is an important task for Natural Language Understanding. It is concerned with classifying the logical relation between two sentences. In this paper, we propose several text generative neural networks for…

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…

Neural text detectors are models trained to detect whether a given text was generated by a language model or written by a human. In this paper, we investigate three simple and resource-efficient strategies (parameter tweaking, prompt…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

Most weakly supervised named entity recognition (NER) models rely on domain-specific dictionaries provided by experts. This approach is infeasible in many domains where dictionaries do not exist. While a phrase retrieval model was used to…

To protect privacy and prevent malicious use of deepfake, current studies propose methods that interfere with the generation process, such as detection and destruction approaches. However, these methods suffer from sub-optimal…

Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While…

User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written…

Deep neural networks have significantly improved the performance of face forgery detection models in discriminating Artificial Intelligent Generated Content (AIGC). However, their security is significantly threatened by the injection of…

Natural Language Processing (NLP) models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling…

Recent studies show that text to image (T2I) diffusion models are vulnerable to backdoor attacks, where a trigger in the input prompt can steer generation toward harmful or unintended content. Beyond the trigger token itself, backdoor…