相关论文: Certifying Language Model Robustness with Fuzzed R…

Randomized smoothing is the current state-of-the-art method for producing provably robust classifiers. While randomized smoothing typically yields robust $\ell_2$-ball certificates, recent research has generalized provable robustness to…

Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit unauthorized or malicious responses. In this paper, we…

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…

Randomized smoothing is considered to be the state-of-the-art provable defense against adversarial perturbations. However, it heavily exploits the fact that classifiers map input objects to class probabilities and do not focus on the ones…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in isolation. This limitation becomes critical in multimodal…

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we…

Modern computing systems heavily rely on hardware as the root of trust. However, their increasing complexity has given rise to security-critical vulnerabilities that cross-layer at-tacks can exploit. Traditional hardware vulnerability…

Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research attempts to mitigate backdoor learning while training the LMs…

Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes.…

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations. Under the paradigm, the robustness of a classifier is aligned with the…

Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to $\ell_2$-adversarial perturbations, viz., by averaging its predictions over the noise via randomized smoothing. Under the…

As large language models (LLMs) expose systemic security challenges in high risk applications, including privacy leaks, bias amplification, and malicious abuse, there is an urgent need for a dynamic risk assessment and collaborative defence…

Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle…

The integration of large language models (LLMs) into robotic control pipelines enables natural language interfaces that translate user prompts into executable commands. However, this digital-to-physical interface introduces a critical and…

The current state-of-the-art defense methods against adversarial examples typically focus on improving either empirical or certified robustness. Among them, adversarially trained (AT) models produce empirical state-of-the-art defense…

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…