相关论文: Reflected Search Poisoning for Illicit Promotion

Cybercriminals have found in online social networks a propitious medium to spread spam and malicious content. Existing techniques for detecting spam include predicting the trustworthiness of accounts and analyzing the content of these…

The rapid growth in popularity and hype surrounding digital assets such as art, video, and music in the form of non-fungible tokens (NFTs) has made them a lucrative investment opportunity, with NFT-based sales surpassing $25B in 2021 alone.…

Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles…

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

Digital commerce thrives on advertising, with many of the largest technology companies relying on it as a significant source of revenue. However, in the context of information-seeking behavior, such as search, advertising may degrade the…

Phishing is the number one threat in the world of internet. Phishing attacks are from decades and with each passing year it is becoming a major problem for internet users as attackers are coming with unique and creative ideas to breach the…

As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries…

Recommender systems play a crucial role in helping users to find their interested information in various web services such as Amazon, YouTube, and Google News. Various recommender systems, ranging from neighborhood-based,…

Large language model-powered sequential recommender systems (LLM-SRSs) have recently demonstrated remarkable performance, enabling recommendations through prompt-driven inference over user interaction sequences. However, this paradigm also…

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Dense embedding-based text retrieval$\unicode{x2013}$retrieval of relevant passages from corpora via deep learning encodings$\unicode{x2013}$has emerged as a powerful method attaining state-of-the-art search results and popularizing…

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendations, and so on, attackers have strong motivation and incentives to manipulate the ranking list. They could inject malicious comparisons into the…

The emergence of Large Language Model-enhanced Search Engines (LLMSEs) has revolutionized information retrieval by integrating web-scale search capabilities with AI-powered summarization. While these systems demonstrate improved efficiency…

Through the Internet of Things (IoT) the internet scope is established by the integration of physical things to classify themselves into mutual things. A physical thing can be created by this inventive perception to signify itself in the…

In Android apps, their developers frequently place app promotion ads, namely advertisements to promote other apps. Unfortunately, the inadequate vetting of ad content allows malicious developers to exploit app promotion ads as a new…

As a prominent instance of vandalism edits, Wiki search poisoning for illicit promotion is a cybercrime in which the adversary aims at editing Wiki articles to promote illicit businesses through Wiki search results of relevant queries. In…

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…

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…

Due to the growing privacy concerns, decentralization emerges rapidly in personalized services, especially recommendation. Also, recent studies have shown that centralized models are vulnerable to poisoning attacks, compromising their…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…