相关论文: Stealth edits to large language models

Recent research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns: fine-tuning with a few harmful data uploaded from the users can compromise the safety alignment of the model. The attack,…

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

While communication strategies of Large Language Models (LLMs) are crucial for human-LLM interactions, they can also be weaponized to elicit private information, yet such stealthy attacks remain under-explored. This paper introduces the…

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this…

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…

Large language models (LLMs) for code are increasingly used in software development, but they remain static after pretraining while APIs and software libraries continue to evolve. Model editing offers a lightweight alternative to retraining…

Large Language Models' knowledge of how to perform cyber-security attacks, create bioweapons, and manipulate humans poses risks of misuse. Previous work has proposed methods to unlearn this knowledge. Historically, it has been unclear…

Finetuning (pretrained) language models is a standard approach for updating their internal parametric knowledge and specializing them to new tasks and domains. However, the corresponding model weight changes ("weight diffs") are not…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training,…

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing…

Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed as a privacy boundary, we reveal that compromised model…

These days deep neural networks are ubiquitously used in a wide range of tasks, from image classification and machine translation to face identification and self-driving cars. In many applications, a single model error can lead to…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…

Model editing enables targeted updates to the knowledge of large language models (LLMs) with minimal retraining. Among existing approaches, locate-then-edit methods constitute a prominent paradigm: they first identify critical layers, then…

Large Language Models often contain factually incorrect or outdated knowledge, giving rise to model editing methods for precise knowledge updates. However, current mainstream locate-then-edit approaches exhibit a progressive performance…

We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…