23 accepted papers
Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting, since end-users lack training data or prior knowledge of the…
Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce **Trojan-Speak**, an adversarial fine-tuning method that bypasses Anthropic's Constitutional Classifiers. Our approach uses curriculum lea…
As language models (LMs) approach human-level performance, a comprehensive understanding of their behavior becomes crucial. This includes evaluating capabilities, biases, task performance, and alignment with societal values. Extensive initial evaluations, including red teaming and diverse benchmark…
Maybe not. We identify and analyse errors in the popular Massive Multitask Language Understanding (MMLU) benchmark. Even though MMLU is widely adopted, our analysis demonstrates numerous ground truth errors that obscure the true capabilities of LLMs. For example, we find that 57% of the analysed que…
Model NLP models are commonly trained (or fine-tuned) on datasets from untrusted platforms like HuggingFace, posing significant risks of data poisoning attacks. A practical yet underexplored challenge arises when such backdoors are discovered after model deployment, making retraining-required defens
Retrieval Augmented Generation (RAG) frameworks can improve the factual accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models’ static intrinsic knowledge. However, these systems are susceptible to adversarial
Despite the widespread adoption of Large language models (LLMs), their remarkable capabilities remain limited to a few high-resource languages. Additionally, many low-resource languages (e.g. African languages) are often evaluated only on basic text classification tasks due to the lack of appropriat…
Large language models (LLMs) remain prone to factual inaccuracies and computational errors, including hallucinations and mistakes in mathematical reasoning. Recent work augmented LLMs with tools to mitigate these shortcomings, but often requires curated gold tool-use demonstrations. In this paper, w…
Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided in the context—this phenomenon, known as context-memory knowledge conflicts, can lead to undesirable model behaviour, s…
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined — such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that trigger malicious outputs. Despite the increasing support for mu…
Despite the recent progress on scaling multilingual machine translation (MT) to several under-resourced African languages, accurately measuring this progress remains challenging, since evaluation is often performed on n-gram matching metrics such as BLEU, which typically show a weaker correlation wi…
While multilingual machine translation (MNMT) systems hold substantial promise, they also have security vulnerabilities. Our research highlights that MNMT systems can be susceptible to a particularly devious style of backdoor attack, whereby an attacker injects poisoned data into a low-resource lang…
The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including backdoor attacks, where hidden malicious behaviors are trigger…
Recent studies demonstrated that large language models (LLMs) can excel in many tasks via in-context learning (ICL). However, recentworks show that ICL-prompted models tend to produce inaccurate results when presented with adversarial inputs. In this work, we investigate whether augmenting ICL with…
Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be implanted through crafting training instances with a specific textual trigger and a target label. This paper posits that ba…
Automatic evaluation methods for translation often require model training, and thus the availability of parallel corpora limits their applicability to low-resource settings. Round-trip translation is a potential workaround, which can reframe bilingual evaluation into a much simpler monolingual task.…
Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generation APIs, recent work has introduced a watermarking algorithm and utilized the null-hypothesis test as a post-hoc ownership verification o…
The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning as a service (MLaaS) by encapsulating fine-tuned BERT-based…
Neural machine translation (NMT) systems are vulnerable to backdoor attacks, whereby an attacker injects poisoned samples into training such that a trained model produces malicious translations. Nevertheless, there is little research on defending against such backdoor attacks in NMT. In this paper,…
Nowadays, due to the breakthrough in natural language generation (NLG), including machine translation, document summarization, image captioning, etc NLG models have been encapsulated in cloud APIs to serve over half a billion people worldwide and process over one hundred billion word generations per…
Machine-learning-as-a-service (MLaaS) has attracted millions of users to their splendid large-scale models. Although published as black-box APIs, the valuable models behind these services are still vulnerable to imitation attacks. Recently, a series of works have demonstrated that attackers manage t…
This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual data selection method to extract in-domain sentences in the…
Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pretrained language models, such as BERT. This allows corporations to easily build powerful APIs by encapsulating fine-tuned BERT models for downstream tasks. However, when a…