How deep learning sees the world: A survey on adversarial attacks & defenses
JC Costa, T Roxo, H Proença, PRM Inácio - IEEE Access, 2024 - ieeexplore.ieee.org
Deep Learning is currently used to perform multiple tasks, such as object recognition, face
recognition, and natural language processing. However, Deep Neural Networks (DNNs) are …
recognition, and natural language processing. However, Deep Neural Networks (DNNs) are …
Better diffusion models further improve adversarial training
It has been recognized that the data generated by the denoising diffusion probabilistic
model (DDPM) improves adversarial training. After two years of rapid development in …
model (DDPM) improves adversarial training. After two years of rapid development in …
On evaluating adversarial robustness of large vision-language models
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented
performance in response generation, especially with visual inputs, enabling more creative …
performance in response generation, especially with visual inputs, enabling more creative …
Decoupled kullback-leibler divergence loss
In this paper, we delve deeper into the Kullback–Leibler (KL) Divergence loss and
mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) …
mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) …
Robust evaluation of diffusion-based adversarial purification
We question the current evaluation practice on diffusion-based purification methods.
Diffusion-based purification methods aim to remove adversarial effects from an input data …
Diffusion-based purification methods aim to remove adversarial effects from an input data …
Boosting accuracy and robustness of student models via adaptive adversarial distillation
Distilled student models in teacher-student architectures are widely considered for
computational-effective deployment in real-time applications and edge devices. However …
computational-effective deployment in real-time applications and edge devices. However …
Improving generalization of adversarial training via robust critical fine-tuning
Deep neural networks are susceptible to adversarial examples, posing a significant security
risk in critical applications. Adversarial Training (AT) is a well-established technique to …
risk in critical applications. Adversarial Training (AT) is a well-established technique to …