相关论文: UDora: A Unified Red Teaming Framework against LLM…

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…

Effective attribution of Advanced Persistent Threats (APTs) increasingly hinges on the ability to correlate behavioral patterns and reason over complex, varied threat intelligence artifacts. We present AURA (Attribution Using…

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Effective modeling of how human travelers learn and adjust their travel behavior from interacting with transportation systems is critical for system assessment and planning. However, this task is also difficult due to the complex cognition…

Malicious traffic detection is a pivotal technology for network security to identify abnormal network traffic and detect network attacks. Large Language Models (LLMs) are trained on a vast corpus of text, have amassed remarkable…

Large language models (LLMs) have emerged as valuable tools for many natural language understanding tasks. In safety-critical applications such as healthcare, the utility of these models is governed by their ability to generate outputs that…

Language agents are rapidly expanding from single-user assistants to multi-user collaborators in shared workspaces and groups. However, today's language models lack a mechanism for isolating user interactions and concurrent tasks, creating…

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static,…

When we design and deploy an Reinforcement Learning (RL) agent, reward functions motivates agents to achieve an objective. An incorrect or incomplete specification of the objective can result in behavior that does not align with human…

Researchers have started using LLM agents in place of human subjects in behavioural and political-science experiments, often as a cheaper substitute for laboratory pools. The substitution does not hold up in strategic settings: humans and…

The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical…

Large language models (LLMs), in conjunction with various reasoning reinforcement methodologies, have demonstrated remarkable capabilities comparable to humans in fields such as mathematics, law, coding, common sense, and world knowledge.…

While tool learning significantly enhances the capabilities of large language models (LLMs), it also introduces substantial security risks. Prior research has revealed various vulnerabilities in traditional LLMs during tool learning.…

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and…

Automated red teaming can discover rare model failures and generate challenging examples that can be used for training or evaluation. However, a core challenge in automated red teaming is ensuring that the attacks are both diverse and…

While large language models (LLMs) have been thoroughly evaluated for deductive and inductive reasoning, their proficiency in holistic rule learning in interactive environments remains less explored. We introduce RULEARN, a novel benchmark…

Backdoors implanted in pre-trained language models (PLMs) can be transferred to various downstream tasks, which exposes a severe security threat. However, most existing backdoor attacks against PLMs are un-targeted and task-specific. Few…

Large Language Models (LLMs) are evolving at an unprecedented pace and have exhibited considerable capability in the realm of natural language processing (NLP) with world knowledge. Benefiting from ultra-large-scale training corpora, a…