Related papers: ShadowMerge: A Novel Poisoning Attack on Graph-Bas…

The remarkable progress of vision-language models (VLMs) has enabled GUI agents to interact with computers in a human-like manner. Yet real-world computer-use tasks remain difficult due to long-horizon workflows, diverse interfaces, and…

Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated the potential of such attacks, they typically rely on…

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence…

Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or…

Attention mechanisms are critical to the success of large language models (LLMs), driving significant advancements in multiple fields. However, for graph-structured data, which requires emphasis on topological connections, they fall short…

Graph neural network (GNN) have demonstrated exceptional performance in solving critical problems across diverse domains yet remain susceptible to backdoor attacks. Existing studies on backdoor attack for graph classification are limited to…

Retrieval-Augmented Generation (RAG) empowers Large Language Models (LLMs) to dynamically integrate external knowledge during inference, improving their factual accuracy and adaptability. However, adversaries can inject poisoned external…

Memory poisoning attacks for Agentic AI and multi-agent systems (MAS) have recently caught attention. It is partially due to the fact that Large Language Models (LLMs) facilitate the construction and deployment of agents. Different memory…

Large Language Models (LLMs) offer significant promise for intelligent traffic management; however, current chain-based systems like TrafficGPT are hindered by sequential task execution, high token usage, and poor scalability, making them…

Deep learning is effective in graph analysis. It is widely applied in many related areas, such as link prediction, node classification, community detection, and graph classification etc. Graph embedding, which learns low-dimensional…

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving external data to mitigate hallucinations and outdated knowledge issues. Benefiting from the strong ability in facilitating diverse data sources and…

Analogical reasoning is the process of discovering and mapping correspondences from a target subject to a base subject. As the most well-known computational method of analogical reasoning, Structure-Mapping Theory (SMT) abstracts both…

When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small number of crafted instruction-response pairs that cause the model to embed…

Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially…

The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies…

A significant amount of society's infrastructure can be modeled using graph structures, from electric and communication grids, to traffic networks, to social networks. Each of these domains are also susceptible to the cascading spread of…

Retrieval-Augmented Generation (RAG) has been empirically shown to enhance the performance of large language models (LLMs) in knowledge-intensive domains such as healthcare, finance, and legal contexts. Given a query, RAG retrieves relevant…

Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to boost the capabilities of large language models (LLMs) by incorporating external, up-to-date knowledge sources. However, this introduces a potential vulnerability to…