Adversarial examples by perturbing high-level features in intermediate decoder layers
원문 초록
We propose a novel method for creating adversarial examples. Instead of perturbing pixels, we use an encoder-decoder representation of the input image and perturb intermediate layers in the decoder. This changes the high-level features provided by the generative model. Therefore, our perturbation possesses semantic meaning, such as a longer beak or green tints. We formulate this task as an optimization problem by minimizing the Wasserstein distance between the adversarial and initial images under a misclassification constraint. We employ the projected gradient method with a simple inexact projection. Due to the projection, all iterations are feasible, and our method always generates adversarial images. We perform numerical experiments on the MNIST and ImageNet datasets in both targeted and untargeted settings. We demonstrate that our adversarial images are much less vulnerable to steganographic defence techniques than pixel-based attacks. Moreover, we show that our method modifies key features such as edges and that defence techniques based on adversarial training are vulnerable to our attacks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
High-Frequency Preserving Image Downscaler
Adaptive Visual KV Cache Reuse for Efficient Multi-Turn Iterative Multimodal Reasoning
PACE-dLLM: 확산 언어 모델을 위한 신뢰도 절벽 추정 기반 탄력적 블록 디코딩
PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models
TACG: 확산 언어 모델 디코딩을 위한 궤적 인식 커밋 게이팅
TACG: Trajectory-Aware Commit Gating for Diffusion Language Model Decoding
SpanUQ: 대규모 언어 모델 생성을 위한 스팬 수준 불확실성 정량화
SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation
첫 토큰 브로드캐스터: 트랜스포머에서 언어 정체성과 분산 견고성의 기계론적 기원
First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.