相关论文: Combating Adversarial Attacks with Multi-Agent Deb…

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more…

This study investigates adversarial attacks conducted to distort voter model dynamics in complex networks. Specifically, a simple adversarial attack method is proposed to hold the state of opinions of an individual closer to the target…

Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data. To improve models beyond the training data, recent works have explored how LLMs can be used to…

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…

When LLM-based multi-agent systems disagree, current practice treats this as noise to be resolved through consensus. We propose it can be signal. We focus on hate speech moderation, a domain where judgments depend on cultural context and…

Single-agent reinforcement learning algorithms in a multi-agent environment are inadequate for fostering cooperation. If intelligent agents are to interact and work together to solve complex problems, methods that counter non-cooperative…

Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow. By decomposing difficult tasks with long contexts into shorter,…

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this work, we study a practical yet largely unexplored attack scenario, the discussion-monitored scenario,…

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

The rapid growth of Large Language Models (LLMs) presents significant privacy, security, and ethical concerns. While much research has proposed methods for defending LLM systems against misuse by malicious actors, researchers have recently…

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

LLM agents are increasingly deployed to plan, retrieve, and write with tools, yet evaluation still leans on static benchmarks and small human studies. We present the Agent-Testing Agent (ATA), a meta-agent that combines static code…

Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augmented generation (RAG) and multi-agent debate (MAD) address this, they are limited by…

Deep learning models have been used for a wide variety of tasks. They are prevalent in computer vision, natural language processing, speech recognition, and other areas. While these models have worked well under many scenarios, it has been…

Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings. However, the majority of existing methodologies for identifying biases in…

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…

Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator. To obtain an effective and robust policy, this simulator should generate user behaviour that is both realistic and varied. Current…

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic…

Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. Existing adversarial defense techniques attempt to reconstruct adversarial examples within feature or text spaces. However, these methods…