Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training (AT) methods …
Protecting the intellectual property of Large Language Models (LLMs) has become increasingly critical due to the high cost of training. Model merging, which integrates multiple expert models into a single multi-task model, introduces a novel risk of …
Although adversarial training has been the state-of-the-art approach to defend against adversarial examples (AEs), it suffers from a robustness-accuracy trade-off, where high robustness is achieved at the cost of clean accuracy. In this work, we …
Infrared detection is an emerging technique for safety-critical tasks owing to its remarkable anti-interference capability. However, recent studies have revealed that it is vulnerable to physically-realizable adversarial patches, posing risks in its …
Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on in-domain …
Deep neural networks are vulnerable to adversarial examples (AEs), which have adversarial transferability: AEs generated for the source model can mislead another (target) model’s predictions. However, the transferability has not been understood in …
It is a problem that as the spread of solar power generation expands, the net power demand sharply fluctuates between day and night. The P2P (Peer to Peer) Electricity Market is expected to be a solution when accumulator-users play an important role. …
ビッグデータの分析を通じた消費者の趣味嗜好の理解とそれによる効率的な顧客獲得が広く試みられてい る。顧客の年齢・職業といった基本情報や購買履歴の分析から得られる情報は効果的であるが、多様な消費者の嗜 好を考慮すると、より多角的な視点からの消費者の購買心理の理解が必要である。本研究では、消費者の基本情報・ 内面・価値観・行動に関する計 2000 項目ほどの多角的なアンケートデータから「飲食店への来店頻度」を予測する タスクを通じて、各サービスを利用する消費者に特有の特徴量の集合の抽出を行った。結 …