相关论文: Well, that escalated quickly: The Single-Turn Cres…

With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…

Large language models (LLMs) have revolutionized how we interact with machines. However, this technological advancement has been paralleled by the emergence of "Mallas," malicious services operating underground that exploit LLMs for…

Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We…

We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking…

Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent…

We introduce the Context Compliance Attack (CCA), a novel, optimization-free method for bypassing AI safety mechanisms. Unlike current approaches -- which rely on complex prompt engineering and computationally intensive optimization -- CCA…

In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifier. A concerning observation is that a significant portion…

Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…

Large Language Models (LLMs) are commonly finetuned for a variety of use cases and domains. A common approach is to leverage Low-Rank Adaptation (LoRA) -- known to provide strong performance at low resource costs. In this study, we…

State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-timestep processing,…

Ensuring the security of large language models (LLMs) is an ongoing challenge despite their widespread popularity. Developers work to enhance LLMs security, but vulnerabilities persist, even in advanced versions like GPT-4. Attackers…

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…

The integration of large language models (LLMs) into information retrieval systems introduces new attack surfaces, particularly for adversarial ranking manipulations. We present $\textbf{StealthRank}$, a novel adversarial attack method that…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

While Large Language Models (LLMs) excel in general domains, their reliability often falls short in scientific problem-solving. The advancement of scientific AI depends on large-scale, high-quality corpora. However, existing scientific…

Pre-trained language models (PLMs) are shown to be vulnerable to minor word changes, which poses a big threat to real-world systems. While previous studies directly focus on manipulating word inputs, they are limited by their means of…

Advanced Persistent Threats (APTs) are prolonged, stealthy intrusions by skilled adversaries that compromise high-value systems to steal data or disrupt operations. Reconstructing complete attack chains from massive, heterogeneous logs is…

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety…