English
Related papers

Related papers: Layer-Wise Perturbations via Sparse Autoencoders f…

200 papers

Reinforcement learning from human feedback (RLHF) is a key paradigm for aligning large language models (LLMs) with human values, yet the reward models at its core remain largely opaque. In this work, we present Sparse Autoencoder For…

Computation and Language · Computer Science 2026-02-02 Wei Shi , Ziyuan Xie , Sihang Li , Xiang Wang

As a fundamental task in Information Retrieval and Computational Linguistics, sentence representation has profound implications for a wide range of practical applications such as text clustering, content analysis, question-answering…

Computation and Language · Computer Science 2025-05-02 Bowen Zhang , Zixin Song , Chunping Li

Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle distinct semantic features. In this paper, we investigate attention query activations as a…

Machine Learning · Computer Science 2026-05-25 Sumanta Bhattacharyya , Pedram Rooshenas

Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer…

Computation and Language · Computer Science 2023-06-09 Lifan Yuan , Yichi Zhang , Yangyi Chen , Wei Wei

We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks while at the same time preserving the semantics and syntax of…

Computation and Language · Computer Science 2020-08-17 Rahul Singh , Tarun Joshi , Vijayan N. Nair , Agus Sudjianto

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Machine Learning · Computer Science 2025-07-30 Viktoria Schuster

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Machine Learning · Computer Science 2026-02-03 Jack Gallifant , Shan Chen , Kuleen Sasse , Hugo Aerts , Thomas Hartvigsen , Danielle S. Bitterman

While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce…

Cryptography and Security · Computer Science 2025-02-04 Ziyi Yin , Yuanpu Cao , Han Liu , Ting Wang , Jinghui Chen , Fenhlong Ma

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du

The growing demand for robots to operate effectively in diverse environments necessitates the need for robust real-time anomaly detection techniques during robotic operations. However, deep learning-based models in robotics face significant…

Robotics · Computer Science 2025-06-24 Taewook Kang , Bum-Jae You , Juyoun Park , Yisoo Lee

In this paper, we present a novel algorithm, FastWordBug, to efficiently generate small text perturbations in a black-box setting that forces a sentiment analysis or text classification mode to make an incorrect prediction. By combining the…

Computation and Language · Computer Science 2020-02-04 Dou Goodman , Lv Zhonghou , Wang minghua

Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with…

Machine Learning · Computer Science 2018-12-19 Emilio Rafael Balda , Arash Behboodi , Rudolf Mathar

Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in…

Machine Learning · Computer Science 2018-02-27 Zhengli Zhao , Dheeru Dua , Sameer Singh

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most…

Computation and Language · Computer Science 2021-06-01 Rongzhou Bao , Jiayi Wang , Hai Zhao

We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…

Computer Vision and Pattern Recognition · Computer Science 2019-11-25 Haichao Zhang , Jianyu Wang

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Machine Learning · Computer Science 2026-05-19 George Ma , Zhongyuan Liang , Irene Y. Chen , Somayeh Sojoudi

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…

Artificial Intelligence · Computer Science 2026-05-19 Ouns El Harzli , Hugo Wallner , Yoonsoo Nam , Haixuan Xavier Tao

Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness. Existing attacks are usually realized through word-level or…

Computation and Language · Computer Science 2022-05-25 Yibin Lei , Yu Cao , Dianqi Li , Tianyi Zhou , Meng Fang , Mykola Pechenizkiy

Machine learning has been proven to be susceptible to carefully crafted samples, known as adversarial examples. The generation of these adversarial examples helps to make the models more robust and gives us an insight into the underlying…

Computation and Language · Computer Science 2020-12-29 Sachin Saxena