English
Related papers

Related papers: Adversarial Sparse Teacher: Defense Against Distil…

200 papers

Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples…

Machine Learning · Computer Science 2019-07-17 Xiaowei Zhou , Ivor W. Tsang , Jie Yin

Dataset distillation aims to encapsulate the rich information contained in dataset into a compact distilled dataset but it faces performance degradation as the image-per-class (IPC) setting or image resolution grows larger. Recent…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Lexiao Zou , Gongwei Chen , Yanda Chen , Miao Zhang

Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data…

Computation and Language · Computer Science 2025-06-02 Jongwoo Ko , Tianyi Chen , Sungnyun Kim , Tianyu Ding , Luming Liang , Ilya Zharkov , Se-Young Yun

Detecting unauthorized knowledge distillation from a deployed LLM API is hard because the defender controls neither the attacker's training pipeline nor the next-token logits. Existing defenses operate on the teacher's output tokens --…

Cryptography and Security · Computer Science 2026-05-19 Guang Yang , Amir Ghasemian , Fengchen Liu , Zhong Wang , Ninareh Mehrabi , Homa Hosseinmardi

Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass defense mechanisms.…

Machine Learning · Computer Science 2024-07-16 Xuelong Dai , Kaisheng Liang , Bin Xiao

Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict diffusion scores from noised versions of true samples in a…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Dazhong Shen , Guanglu Song , Yi Zhang , Bingqi Ma , Lujundong Li , Dongzhi Jiang , Zhuofan Zong , Yu Liu

This paper introduces a novel method, Sample-efficient Probabilistic Detection using Extreme Value Theory (SPADE), which transforms a classifier into an abstaining classifier, offering provable protection against out-of-distribution and…

Machine Learning · Statistics 2025-01-20 Nicolas Atienza , Christophe Labreuche , Johanne Cohen , Michele Sebag

Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks--most notably backdoor attacks. Existing KD…

Cryptography and Security · Computer Science 2026-05-26 Shanmin Wang , Dongdong Zhao

Adversarial examples are important for understanding the behavior of neural models, and can improve their robustness through adversarial training. Recent work in natural language processing generated adversarial examples by assuming…

Machine Learning · Computer Science 2019-04-05 Yotam Gil , Yoav Chai , Or Gorodissky , Jonathan Berant

Deep learning classifiers are known to be vulnerable to adversarial examples. A recent paper presented at ICML 2019 proposed a statistical test detection method based on the observation that logits of noisy adversarial examples are biased…

Machine Learning · Computer Science 2019-07-30 Hossein Hosseini , Sreeram Kannan , Radha Poovendran

Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile, dataset distillation has emerged to synthesize a compact dataset that preserves critical…

Cryptography and Security · Computer Science 2026-03-06 Yuchen Shi , Huajie Chen , Heng Xu , Zhiquan Liu , Jialiang Shen , Chi Liu , Shuai Zhou , Tianqing Zhu , Wanlei Zhou

Diffusion models with transformer architectures have demonstrated promising capabilities in generating high-fidelity images and scalability for high resolution. However, iterative sampling process required for synthesis is very…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Yeongmin Kim , Sotiris Anagnostidis , Yuming Du , Edgar Schönfeld , Jonas Kohler , Markos Georgopoulos , Albert Pumarola , Ali Thabet , Artsiom Sanakoyeu

Transfer learning is prevalent as a technique to efficiently generate new models (Student models) based on the knowledge transferred from a pre-trained model (Teacher model). However, Teacher models are often publicly available for sharing…

Machine Learning · Computer Science 2022-02-10 Bang Wu , Shuo Wang , Xingliang Yuan , Cong Wang , Carsten Rudolph , Xiangwen Yang

Despite the empirical success of knowledge distillation, current state-of-the-art methods are computationally expensive to train, which makes them difficult to adopt in practice. To address this problem, we introduce two distinct…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Roy Miles , Adrian Lopez Rodriguez , Krystian Mikolajczyk

The knowledge distillation uses a high-performance teacher network to guide the student network. However, the performance gap between the teacher and student networks can affect the student's training. This paper proposes a novel knowledge…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Songling Zhu , Ronghua Shang , Bo Yuan , Weitong Zhang , Yangyang Li , Licheng Jiao

Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial…

Machine Learning · Computer Science 2019-11-25 Sambuddha Saha , Aashish Kumar , Pratyush Sahay , George Jose , Srinivas Kruthiventi , Harikrishna Muralidhara

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by…

Machine Learning · Computer Science 2019-08-08 Hao-Yun Chen , Jhao-Hong Liang , Shih-Chieh Chang , Jia-Yu Pan , Yu-Ting Chen , Wei Wei , Da-Cheng Juan

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…

Machine Learning · Computer Science 2026-05-26 Changyu Chen , Xiting Wang , Rui Yan

Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Alessandro Cennamo , Ido Freeman , Anton Kummert

Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on…

Machine Learning · Computer Science 2021-04-06 Emilio Parisotto , Ruslan Salakhutdinov