Search Results for author:
Found 6 papers, 3 papers with code
InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
Initially, we utilize a public text-to-image generative model to "reverse" the target response into a target image, and employ GPT-4 to infer a reasonable instruction $\boldsymbol{p}^\prime$ from the target response.
Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval
Further, we, for the first time, formulate the formalized adversarial training of deep hashing into a unified minimax optimization under the guidance of the generated mainstay codes.
Reliable and Efficient Evaluation of Adversarial Robustness for Deep Hashing-Based Retrieval
Deep hashing has been extensively applied to massive image retrieval due to its efficiency and effectiveness.
CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrieval
On the one hand, CgAT generates the worst adversarial examples as augmented data by maximizing the Hamming distance between the hash codes of the adversarial examples and the center codes.
Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing
However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field.
Initializing Perturbations in Multiple Directions for Fast Adversarial Training
Recent developments in the filed of Deep Learning have demonstrated that Deep Neural Networks(DNNs) are vulnerable to adversarial examples.
