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

Randomized Smoothing (RS), being one of few provable defenses, has been showing great effectiveness and scalability in terms of defending against $\ell_2$-norm adversarial perturbations. However, the cost of MC sampling needed in RS for…

Large Language Models (LLMs) have gained widespread use in various applications due to their powerful capability to generate human-like text. However, prompt injection attacks, which involve overwriting a model's original instructions with…

Federated learning (FL) represents a novel paradigm to machine learning, addressing critical issues related to data privacy and security, yet suffering from data insufficiency and imbalance. The emergence of foundation models (FMs) provides…

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat…

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…

Language-empowered foundation models (LeFMs), such as CLIP and GraphCLIP, have transformed multimodal learning by aligning visual (or graph) features with textual representations, enabling powerful downstream capabilities like few-shot…

Large web-scale datasets have driven the rapid advancement of pre-trained language models (PLMs), but unauthorized data usage has raised serious copyright concerns. Existing dataset ownership verification (DOV) methods typically assume that…

Machine learning (ML) techniques are increasingly common in security applications, such as malware and intrusion detection. However, ML models are often susceptible to evasion attacks, in which an adversary makes changes to the input (such…

Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks, including evasion and backdoor (poisoning) attacks. On the defense side, there have been intensive efforts on improving both empirical and…

Neural ranking models have achieved remarkable progress and are now widely deployed in real-world applications such as Retrieval-Augmented Generation (RAG). However, like other neural architectures, they remain vulnerable to adversarial…

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.…

Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input samples. Defending against such attacks is highly…

Randomness supports many critical functions in the field of machine learning (ML) including optimisation, data selection, privacy, and security. ML systems outsource the task of generating or harvesting randomness to the compiler, the cloud…

It is imperative to ensure the stability of every prediction made by a language model; that is, a language's prediction should remain consistent despite minor input variations, like word substitutions. In this paper, we investigate the…

This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We…

Certified defenses such as randomized smoothing have shown promise towards building reliable machine learning systems against $\ell_p$-norm bounded attacks. However, existing methods are insufficient or unable to provably defend against…

In the modern era where software plays a pivotal role, software security and vulnerability analysis are essential for secure software development. Fuzzing test, as an efficient and traditional software testing method, has been widely…