paper-with-me

홈 › Papers

Adversarial Search Engine Optimization for Large Language Models

2024-06-26 · Fredrik Nestaas, Edoardo Debenedetti, Florian Tramèr

Large Language Models (LLMs) are increasingly used in applications where the model selects from competing third-party content, such as in LLM-powered search engines or chatbot plugins. In this paper, we introduce Preference Manipulation Attacks, a new class of attacks that manipulate an LLM's selections to favor the attacker. We demonstrate that carefully crafted website content or plugin documentations can trick an LLM to promote the attacker products and discredit competitors, thereby increasing user traffic and monetization. We show this leads to a prisoner's dilemma, where all parties are incentivized to launch attacks, but the collective effect degrades the LLM's outputs for everyone. We demonstrate our attacks on production LLM search engines (Bing and Perplexity) and plugin APIs (for GPT-4 and Claude). As LLMs are increasingly used to rank third-party content, we expect Preference Manipulation Attacks to emerge as a significant threat.

📄 PDF Abstract BibTeX arXiv:2406.18382

Code (0)

등록된 구현이 없습니다.

Tasks

Chatbot

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

White Hat Search Engine Optimization using Large Language Models

2025-02-11 · Niv Bardas, Tommy Mordo, Oren Kurland, Moshe Tennenholtz 외

We present novel white-hat search engine optimization techniques based on genAI and demonstrate their empirical merits.

Document Ranking

Unleashing the potential of prompt engineering for large language models

2023-10-23 · Banghao Chen, Zhaofeng Zhang, Nicolas Langrené, Shengxin Zhu

This comprehensive review delves into the pivotal role of prompt engineering in unleashing the capabilities of Large Language Models (LLMs). The development of Artificial Intelligence (AI), from its inception in the 1950…

HallucinationPrompt EngineeringPrompt Learning

Ranking Manipulation for Conversational Search Engines

2024-06-05 · Samuel Pfrommer, Yatong Bai, Tanmay Gautam, Somayeh Sojoudi

Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These conversational search engines operate by loading retrieved website text into the LLM…

Conversational SearchLanguage ModelingLanguage ModellingLarge Language Model

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models

2024-04-21 · Yihao Zhang, Zeming Wei, Jun Sun, Meng Sun

Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to int…

Generative Adversarial NetworkModel Editing

Evaluating Robustness of Generative Search Engine on Adversarial Factual Questions

2024-02-25 · Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li 외

Generative search engines have the potential to transform how people seek information online, but generated responses from existing large language models (LLMs)-backed generative search engines may not always be accurate…

RetrievalRetrieval-augmented Generation