Large Language Models (LLMs), which bridge the gap between human language
understanding and complex problem-solving, achieve state-of-the-art performance on …

Backdoor Attacks have been a serious vulnerability against Large Language Models
(LLMs). However, previous methods only reveal such risk in specific models, or present …

Retrieval-augmented generation (RAG) has been shown vulnerable to retrieval corruption
attacks: an attacker can inject malicious passages into retrieval results to induce inaccurate …

The advancement of Large Language Models (LLMs) has significantly impacted various
domains, including Web search, healthcare, and software development. However, as these …

The robustness of recent Large Language Models (LLMs) has become increasingly crucial
as their applicability expands across various domains and real-world applications. Retrieval …

Recent advances in neural information retrieval (IR) models have significantly enhanced
their effectiveness over various IR tasks. The robustness of these models, essential for …

Pre-training has been a necessary phase for deploying pre-trained language models
(PLMs) to achieve remarkable performance in downstream tasks. However, we empirically …

Parameter-efficient fine-tuning (PEFT) can bridge the gap between large language models
(LLMs) and downstream tasks. However, PEFT has been proven vulnerable to malicious …

Beyond effectiveness, the robustness of an information retrieval (IR) system is increasingly
attracting attention. When deployed, a critical technology such as IR should not only deliver …

Despite being widely applied due to their exceptional capabilities, Large Language Models
(LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce …