相关论文: Unveiling Vulnerability of Self-Attention

Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can leverage inherent weaknesses in the models, resulting in…

Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as tool-returned data, webpages, or MCP context, causing harmful…

In this work, we present a series of structure transformation attacks on LLM alignment, where we encode natural language intent using diverse syntax spaces, ranging from simple structure formats and basic query languages (e.g., SQL) to new…

Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…

Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…

Transformer-based pre-training techniques of text and layout have proven effective in a number of document understanding tasks. Despite this success, multimodal pre-training models suffer from very high computational and memory costs.…

Large Vision-Language Models (LVLMs) are foundational to modern multimodal applications, yet their susceptibility to adversarial attacks remains a critical concern. Prior white-box attacks rarely generalize across tasks, and black-box…

In this work, we study how multi-head latent attention (MLA), a popular strategy for compressing key/value memory, affects a transformer's internal capacity during pretraining. Using a lightweight suite of Marchenko-Pastur (MP) diagnostics,…

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

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), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a vulnerability, allowing even…

The growth of highly advanced Large Language Models (LLMs) constitutes a huge dual-use problem, making it necessary to create dependable AI-generated text detection systems. Modern detectors are notoriously vulnerable to adversarial…

Recursion is a prominent feature of human language, and fundamentally challenging for self-attention due to the lack of an explicit recursive-state tracking mechanism. Consequently, Transformer language models poorly capture long-tail…

Modern text-to-speech (TTS) systems, particularly those built on Large Audio-Language Models (LALMs), generate high-fidelity speech that faithfully reproduces input text and mimics specified speaker identities. While prior misuse studies…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data. The resulting models are too large for on-edge applications. For instance, BERT-based…

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…