Large Language Models as Carriers of Hidden Messages

• URL: http://arxiv.org/abs/2406.02481v4
• Date: Tue, 24 Sep 2024 12:00:29 GMT
• Title: Large Language Models as Carriers of Hidden Messages
• Authors: Jakub Hoscilowicz, Pawel Popiolek, Jan Rudkowski, Jedrzej Bieniasz, Artur Janicki,
• Abstract summary: Simple fine-tuning can embed hidden text into large language models (LLMs), which is revealed only when triggered by a specific query. Our work demonstrates that embedding hidden text via fine-tuning, although seemingly secure due to the vast number of potential triggers, is vulnerable to extraction. We introduce an extraction attack called Unconditional Token Forcing (UTF), which iteratively feeds tokens from the LLM's vocabulary to reveal sequences with high token probabilities, indicating hidden text candidates.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simple fine-tuning can embed hidden text into large language models (LLMs), which is revealed only when triggered by a specific query. Applications include LLM fingerprinting, where a unique identifier is embedded to verify licensing compliance, and steganography, where the LLM carries hidden messages disclosed through a trigger query. Our work demonstrates that embedding hidden text via fine-tuning, although seemingly secure due to the vast number of potential triggers, is vulnerable to extraction through analysis of the LLM's output decoding process. We introduce an extraction attack called Unconditional Token Forcing (UTF), which iteratively feeds tokens from the LLM's vocabulary to reveal sequences with high token probabilities, indicating hidden text candidates. We also present Unconditional Token Forcing Confusion (UTFC), a defense paradigm that makes hidden text resistant to all known extraction attacks without degrading the general performance of LLMs compared to standard fine-tuning. UTFC has both benign (improving LLM fingerprinting) and malign applications (using LLMs to create covert communication channels).

Related papers

• LLMmap: Fingerprinting For Large Language Models [15.726286532500971]
  With as few as 8 interactions, LLMmap can accurately identify 42 different LLM versions with over 95% accuracy. We discuss potential mitigations and demonstrate that, against resourceful adversaries, effective countermeasures may be challenging or even unrealizable.
  arXiv  Detail & Related papers  (2024-07-22T17:59:45Z)
• Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context [49.13497493053742]
  This research explores converting a nonsensical suffix attack into a sensible prompt via a situation-driven contextual re-writing. We combine an independent, meaningful adversarial insertion and situations derived from movies to check if this can trick an LLM. Our approach demonstrates that a successful situation-driven attack can be executed on both open-source and proprietary LLMs.
  arXiv  Detail & Related papers  (2024-07-19T19:47:26Z)
• Are you still on track!? Catching LLM Task Drift with Activations [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users. We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set. We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering [9.86691461253151]
  We introduce a novel method for attribution in contextual question answering, leveraging the hidden state representations of large language models (LLMs) Our approach bypasses the need for extensive model retraining and retrieval model overhead, offering granular attributions and preserving the quality of generated answers. We present Verifiability-granular, an attribution dataset which has token level annotations for LLM generations in the contextual question answering setup.
  arXiv  Detail & Related papers  (2024-05-28T09:12:44Z)
• Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization [12.885866125783618]
  Large Language Models (LLMs) tend to produce inaccurate responses to specific queries. We construct an adversarial dataset, named as $textbfADT (Adrial dataset for Tokenizer)$ to challenge LLMs' tokenization. Our empirical results reveal that our ADT is highly effective on challenging the tokenization of leading LLMs, including GPT-4o, Llama-3, Qwen2.5-max and so on.
  arXiv  Detail & Related papers  (2024-05-27T11:39:59Z)
• DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers [80.18953043605696]
  We introduce an automatic prompt textbfDecomposition and textbfReconstruction framework for jailbreak textbfAttack (DrAttack) DrAttack includes three key components: (a) Decomposition' of the original prompt into sub-prompts, (b) Reconstruction' of these sub-prompts implicitly by in-context learning with semantically similar but harmless reassembling demo, and (c) a Synonym Search' of sub-prompts, aiming to find sub-prompts' synonyms that maintain the original intent while
  arXiv  Detail & Related papers  (2024-02-25T17:43:29Z)
• Towards Verifiable Text Generation with Symbolic References [27.01624440701639]
  We propose symbolically grounded generation (SymGen) as a simple approach for enabling easier manual validation of an LLM's output. SymGen prompts an LLM to interleave its regular output text with explicit symbolic references to fields present in some conditioning data. Across a range of data-to-text and question-answering experiments, we find that LLMs are able to directly output text that makes use of accurate symbolic references while maintaining fluency and factuality.
  arXiv  Detail & Related papers  (2023-11-15T18:28:29Z)
• A Robust Semantics-based Watermark for Large Language Model against Paraphrasing [50.84892876636013]
  Large language models (LLMs) have show great ability in various natural language tasks. There are concerns that LLMs are possible to be used improperly or even illegally. We propose a semantics-based watermark framework SemaMark.
  arXiv  Detail & Related papers  (2023-11-15T06:19:02Z)
• SeqXGPT: Sentence-Level AI-Generated Text Detection [62.3792779440284]
  We introduce a sentence-level detection challenge by synthesizing documents polished with large language models (LLMs) We then propose textbfSequence textbfX (Check) textbfGPT, a novel method that utilizes log probability lists from white-box LLMs as features for sentence-level AIGT detection.
  arXiv  Detail & Related papers  (2023-10-13T07:18:53Z)
• Red Teaming Language Model Detectors with Language Models [114.36392560711022]
  Large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. Recent works have proposed algorithms to detect LLM-generated text and protect LLMs. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation.
  arXiv  Detail & Related papers  (2023-05-31T10:08:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.