Related papers: Certified Robustness for Large Language Models wit…
With the increasing capabilities of large language models (LLMs), these high-performance models have achieved state-of-the-art results on a wide range of natural language processing (NLP) tasks. However, the models' performance on…
Implicit feedback, often used to build recommender systems, unavoidably confronts noise due to factors such as misclicks and position bias. Previous studies have attempted to alleviate this by identifying noisy samples based on their…
Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently,…
Self-Supervised Learning (SSL) has become a powerful solution to extract rich representations from unlabeled data. Yet, SSL research is mostly focused on clean, curated and high-quality datasets. As a result, applying SSL on noisy data…
Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their ability to use bidirectional context and adapt to a specific ASR…
Large language models (LLMs) achieve strong performance but incur high deployment costs, motivating extremely low-bit but lossy quantization. Existing quantization algorithms mainly focus on improving the numerical accuracy of forward…
Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method constructs a smoothed DNN model and certifies its robustness…
The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…
Sequential Recommenders generate recommendations based on users' historical interaction sequences. However, in practice, these collected sequences are often contaminated by noisy interactions, which significantly impairs recommendation…
Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…
The dependence of Natural Language Processing (NLP) intelligent software on Large Language Models (LLMs) is increasingly prominent, underscoring the necessity for robustness testing. Current testing methods focus solely on the robustness of…
The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured…
The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage. These attacks pose significant risks to high-reliability applications,…
Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…
Randomized smoothing has achieved great success for certified robustness against adversarial perturbations. Given any arbitrary classifier, randomized smoothing can guarantee the classifier's prediction over the perturbed input with…
Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Their certified robustness has gained increasing research attention due to security concerns.…
Large Language Models (LLMs) have advanced various Natural Language Processing (NLP) tasks, such as text generation and translation, among others. However, these models often generate texts that can perpetuate biases. Existing approaches to…
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been…
Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…
Large language models (LLMs) are increasingly deployed in multilingual, real-world applications with user inputs -- naturally introducing \emph{typographical errors} (typos). Yet most benchmarks assume clean input, leaving the robustness of…