Related papers: Attention Is Where You Attack
Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge, but its reliance on potentially poisonable knowledge bases introduces new availability risks. Attackers can…
Safety alignment is critical for the ethical deployment of large language models (LLMs), guiding them to avoid generating harmful or unethical content. Current alignment techniques, such as supervised fine-tuning and reinforcement learning…
Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful…
Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…
Large Reasoning Models (LRMs) have demonstrated strong capabilities in generating step-by-step reasoning chains alongside final answers, enabling their deployment in high-stakes domains such as healthcare and education. While prior…
Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods…
Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar…
Large Language Models (LLMs) with safe-alignment training are powerful instruments with robust language comprehension capabilities. These models typically undergo meticulous alignment procedures involving human feedback to ensure the…
The widespread adoption of large language models (LLMs) has raised concerns about their safety and reliability, particularly regarding their vulnerability to adversarial attacks. In this paper, we propose a novel perspective that attributes…
To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…
Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…
As the core operator of Transformers, Softmax Attention exhibits excellent global modeling capabilities. However, its quadratic complexity limits its applicability to vision tasks. In contrast, Linear Attention shares a similar formulation…
In recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end training and often generate noticeable perturbation patches. To…
Efficient communication is critical for decentralized Multi-Robot Path Planning (MRPP), yet existing learned communication methods treat all neighboring robots equally regardless of their spatial proximity, leading to diluted attention in…
Safety alignment in diffusion language models (dLLMs) relies on a single load-bearing assumption: that committed tokens are permanent. We show that violating this assumption, by re-masking committed refusal tokens and injecting a short…
Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to…
Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. However, existing methods often struggle to balance semantic…
We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…
Large Reasoning Models (LRMs) face a distinct safety vulnerability: their internal reasoning chains may generate harmful content even when the final output appears benign. To address this overlooked risk, we first propose a novel attack…
Retrieval-Augmented Generation (RAG) enriches LLMs by dynamically retrieving external knowledge, reducing hallucinations and satisfying real-time information needs. While existing research mainly targets RAG's performance and efficiency,…