按年被提到
20232023 · 1 次2026
AI 安全、伦理与社会影响›模型窃取、记忆与水印·arXiv:2307.10719 · cs.AI

LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?

David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-07-21 · 最近 2025-01-31
2不同的人
2活跃月份
2讨论串
38被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence mechanisms, such as model fine-tuning or output censorship using LLMs, have proven to be fallible, as LLMs can still generate problematic responses. Commonly employed censorship approaches treat the issue as a machine learning problem and rely on another LM to detect undesirable content in LLM outputs. In this paper, we present the theoretical limitations of such semantic censorship approaches. Specifically, we demonstrate that semantic censorship can be perceived as an undecidable problem, highlighting the inherent challenges in censorship that arise due to LLMs' programmatic and instruction-following capabilities. Furthermore, we argue that the challenges extend beyond semantic censorship, as knowledgeable attackers can reconstruct impermissible outputs from a collection of permissible ones. As a result, we propose that the problem of censorship needs to be reevaluated; it should be treated as a security problem which warrants the adaptation of security-based approaches to mitigate potential risks.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论0x7d · 2025-01

“Hi HN! This is my article! It was great to put together a writeup of a fun evening or two of work. It looks like this goes much deeper. I'm learning a lot from some of the linked articles, one of the base hypothesise of my work was that the filtering was distinct from the model, due to the cost of training with pre-filtered or censored data at scale: ht…”

Bypass DeepSeek censorship by speaking in hex原评论 ↗
被提交为 story · 1 次