English
Related papers

Related papers: Verifying LLM Inference to Detect Model Weight Exf…

200 papers

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their…

Computation and Language · Computer Science 2025-01-20 Vinu Sankar Sadasivan , Aounon Kumar , Sriram Balasubramanian , Wenxiao Wang , Soheil Feizi

In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predictions. To prevent model stealing, existing defenses focus…

Cryptography and Security · Computer Science 2022-12-13 Adam Dziedzic , Muhammad Ahmad Kaleem , Yu Shen Lu , Nicolas Papernot

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels. Prior work demonstrated this threat but relied on trivially recoverable encodings. We formalize payload recoverability via classifier accuracy and…

Cryptography and Security · Computer Science 2026-02-02 Charles Westphal , Keivan Navaie , Fernando E. Rosas

Machine learning (ML) has been widely adopted in various privacy-critical applications, e.g., face recognition and medical image analysis. However, recent research has shown that ML models are vulnerable to attacks against their training…

Machine Learning · Computer Science 2021-09-20 Zheng Li , Yang Zhang

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Cryptography and Security · Computer Science 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

Cryptography and Security · Computer Science 2026-01-01 Yuan Xin , Dingfan Chen , Linyi Yang , Michael Backes , Xiao Zhang

Distribution inference, sometimes called property inference, infers statistical properties about a training set from access to a model trained on that data. Distribution inference attacks can pose serious risks when models are trained on…

Machine Learning · Computer Science 2022-07-06 Anshuman Suri , David Evans

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

Cryptography and Security · Computer Science 2026-02-27 Piyush Jaiswal , Aaditya Pratap , Shreyansh Saraswati , Harsh Kasyap , Somanath Tripathy

Machine learning models have been shown to be vulnerable to membership inference attacks, i.e., inferring whether individuals' data have been used for training models. The lack of understanding about factors contributing success of these…

Machine Learning · Computer Science 2020-04-29 Farhad Farokhi , Mohamed Ali Kaafar

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…

Computation and Language · Computer Science 2025-02-24 Tianlong Li , Zhenghua Wang , Wenhao Liu , Muling Wu , Shihan Dou , Changze Lv , Xiaohua Wang , Xiaoqing Zheng , Xuanjing Huang

Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary data holders who are not ML experts can apply off-the-shelf…

Cryptography and Security · Computer Science 2024-07-03 Zitao Chen , Karthik Pattabiraman

Before adopting a new large language model (LLM) architecture, it is critical to understand vulnerabilities accurately. Existing evaluations can be difficult to trust, often drawing conclusions from LLMs that are not meaningfully…

Cryptography and Security · Computer Science 2025-10-08 Mary Llewellyn , Annie Gray , Josh Collyer , Michael Harries

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Machine Learning · Computer Science 2026-02-02 Jiawei Li

Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows…

Cryptography and Security · Computer Science 2026-04-13 Dennis Rall , Bernhard Bauer , Mohit Mittal , Thomas Fraunholz

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…

Cryptography and Security · Computer Science 2024-10-31 David Glukhov , Ziwen Han , Ilia Shumailov , Vardan Papyan , Nicolas Papernot

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

Cryptography and Security · Computer Science 2020-09-02 Shadi Rahimian , Tribhuvanesh Orekondy , Mario Fritz

Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we study membership inference in the white-box setting in…

Machine Learning · Computer Science 2020-06-26 Klas Leino , Matt Fredrikson

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated…

Cryptography and Security · Computer Science 2026-02-27 Qianlong Lan , Anuj Kaul , Shaun Jones , Stephanie Westrum