相关论文: A Girl Has A Name: Detecting Authorship Obfuscatio…

Watermarking is a key technique for detecting AI-generated text. In this work, we study its vulnerabilities and introduce the Smoothing Attack, a novel watermark removal method. By leveraging the relationship between the model's confidence…

Large language models are known to produce outputs that are plausible but factually incorrect. To prevent people from making erroneous decisions by blindly trusting AI, researchers have explored various ways of communicating factuality…

There are numerous opportunities for adversaries to observe user behavior remotely on the web. Additionally, keystroke biometric algorithms have advanced to the point where user identification and soft biometric trait recognition rates are…

Deep neural networks are vulnerable to adversarial examples, which dramatically alter model output using small input changes. We propose Neural Fingerprinting, a simple, yet effective method to detect adversarial examples by verifying…

Authorship verification is the task of determining if two distinct writing samples share the same author and is typically concerned with the attribution of written text. In this paper, we explore the attribution of transcribed speech, which…

This work addresses the timely yet underexplored problem of performing inference and finetuning of a proprietary LLM owned by a model provider entity on the confidential/private data of another data owner entity, in a way that ensures the…

Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the…

Online behavioral advertising, and the associated tracking paraphernalia, poses a real privacy threat. Unfortunately, existing privacy-enhancing tools are not always effective against online advertising and tracking. We propose Harpo, a…

Software obfuscation is a crucial technology to protect intellectual property and manage digital rights within our society. Despite its huge practical importance, both commercial and academic state-of-the-art obfuscation methods are…

Deidentification seeks to anonymize textual data prior to distribution. Automatic deidentification primarily uses supervised named entity recognition from human-labeled data points. We propose an unsupervised deidentification method that…

Warnings have been raised about the steady diminution of privacy. More and more personal information, such as that contained electronic mail, is moving to cloud computing servers where it might be machine-searched and indexed. FauxCrypt is…

Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to…

In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection. We employ adversarial perturbations for obfuscating certain variables in raw data…

Despite their prevalence in society, social biases are difficult to identify, primarily because human judgements in this domain can be unreliable. We take an unsupervised approach to identifying gender bias against women at a comment level…

As billions of personal data being shared through social media and network, the data privacy and security have drawn an increasing attention. Several attempts have been made to alleviate the leakage of identity information from face photos,…

This paper presents a survey of text steganography methods used for hid- ing secret information inside some covertext. Widely known hiding techniques (such as translation based steganography, text generating and syntactic embed- ding) and…

Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

For centuries, writers have hidden messages in their texts as acrostics, where initial letters of consecutive lines or paragraphs form meaningful words or phrases. Scholars searching for acrostics manually can only focus on a few authors at…

Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation varies with the data domain, privacy objectives, and downstream application. However, existing…