Related papers: Defending Against Backdoor Attacks in Natural Lang…
Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…
Backdoor (Trojan) attacks are emerging threats against deep neural networks (DNN). A DNN being attacked will predict to an attacker-desired target class whenever a test sample from any source class is embedded with a backdoor pattern; while…
Backdoor attacks pose a significant security threat to natural language processing (NLP) systems, but existing methods lack explainable trigger mechanisms and fail to quantitatively model vulnerability patterns. This work pioneers the…
Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural…
Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…
Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…
Backdoor attacks have become a critical threat to deep neural networks (DNNs), drawing many research interests. However, most of the studied attacks employ a single type of trigger. Consequently, proposed backdoor defenders often rely on…
With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…
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…
The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…
Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems with opposite objectives: NLU tackles the transformation from natural language to…
Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable to backdoor attacks, where models behave normally for…
As large language models (LLMs) continue to evolve, it is critical to assess the security threats and vulnerabilities that may arise both during their training phase and after models have been deployed. This survey seeks to define and…
Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…
Natural Language Generation (NLG) has made great progress in recent years due to the development of deep learning techniques such as pre-trained language models. This advancement has resulted in more fluent, coherent and even properties…
Recent language models, especially those based on recurrent neural networks (RNNs), make it possible to generate natural language from a learned probability. Language generation has wide applications including machine translation,…
It has been proved that deep neural networks are facing a new threat called backdoor attacks, where the adversary can inject backdoors into the neural network model through poisoning the training dataset. When the input containing some…
Generative language models are increasingly used for contract drafting and enhancement, creating a scenario where competing parties deploy different language models against each other. This introduces not only a game-theory challenge but…
Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…
Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…