8 accepted papers
In this work, we investigate the risks of collective financial fraud in large-scale multi-agent systems, driven by large language model (LLM) agents. We examine whether agents can collaborate in fraudulent activities, amplify the risks of such behaviors, and identify factors critical to fraud succes…
The capabilities of large language models (LLMs), particularly large reasoning models (LRMs), are rapidly advancing. This raises concerns about whether LRMs can maintain their safety awareness throughout long-form reasoning. Frustratingly, we identify a prevalent safety issue across LLMs and LRMs, w…
Planning has become a central capability for contemporary agent systems in navigating complex, long-horizon tasks, yet existing approaches predominantly rely on fixed, hand-crafted planning structures that lack the flexibility to adapt to the structural diversity of open-ended problems. To address t…
Safety concerns in large language models (LLMs) have gained significant attention due to their exposure to potentially harmful data during pre-training. In this paper, we identify a new safety vulnerability in LLMs: their susceptibility to natural distribution shifts between attack prompts and origi…
The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from human feedback have enhanced their safety, these methods prim…
Solving combinatorial optimization (CO) on graphs has been attracting increasing interests from the machine learning community whereby data-driven approaches were recently devised to go beyond traditional manually-designated algorithms. In this paper, we study the robustness of a combinatorial solve…
Despite the recent breakthrough of high accuracy deep graph matching (GM) over visual images, the robustness of deep GM models is rarely studied which yet has been revealed an important issue in modern deep nets, ranging from image recognition to graph learning tasks. We first show that an adversari…
The existence of adversarial examples poses concerns for the robustness of convolutional neural networks (CNN), for which a popular hypothesis is about the frequency bias phenomenon: CNNs rely more on high-frequency components (HFC) for classification than humans, which causes the brittleness of CNN…