Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systems
원문 초록
Due to the numerous advantages of machine learning (ML) algorithms, many applications now incorporate them. However, many studies in the field of image classification have shown that MLs can be fooled by a variety of adversarial attacks. These attacks take advantage of ML algorithms' inherent vulnerability. This raises many questions in the cybersecurity field, where a growing number of researchers are recently investigating the feasibility of such attacks against machine learning-based security systems, such as intrusion detection systems. The majority of this research demonstrates that it is possible to fool a model using features extracted from a raw data source, but it does not take into account the real implementation of such attacks, i.e., the reverse transformation from theory to practice. The real implementation of these adversarial attacks would be influenced by various constraints that would make their execution more difficult. As a result, the purpose of this study was to investigate the actual feasibility of adversarial attacks, specifically evasion attacks, against network-based intrusion detection systems (NIDS), demonstrating that it is entirely possible to fool these ML-based IDSs using our proposed adversarial algorithm while assuming as many constraints as possible in a black-box setting. In addition, since it is critical to design defense mechanisms to protect ML-based IDSs against such attacks, a defensive scheme is presented. Realistic botnet traffic traces are used to assess this work. Our goal is to create adversarial botnet traffic that can avoid detection while still performing all of its intended malicious functionality.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
억제적 셀프-어텐션: 비전 트랜스포머에서 초점 선명화
Inhibited Self-Attention: Sharpening Focus in Vision Transformers
비전 트랜스포머(ViT)는 컴퓨터 비전(CV) 과제에서 뛰어난 성능을 보여 왔다. 그러나 셀프-어텐션 메커니즘은 종종 배경 영역 전반에 초점을 분산시키며, 객체 관련 단서보다는 가짜 상관관계에 의존하는 경향이 있다. 생물학적 시각 시스템에서 관찰되는 억제 메커니즘에서 영감을 받아, 억제 신호를 통합하여 특징 선택성을 높이고 가짜 반응을 억제하는 새로운 셀프-어텐션인 억제적 셀프-어텐션(ISA)을 제안한다. 소프트맥스 정규화로 인해 양의 어텐션 값에만 의존하는 기존 셀프-어텐션과 달리, 우리 접근법은 음의 어텐션 점수를 유지하고 활용하여 무관한 특징을 억제하고 관심 객체에 대한 초점을 선명하게 한다. ImageNet-1k와 COCO를 포함한 여러 데이터셋과 여러 견고성 벤치마크에 걸친 실험은 ISA가 객체 중심 선택성을 높이고, 지름길 의존을 줄이며, 분포 외 일반화를 개선함을 보여 준다. 관련성 맵 분석은 ISA를 적용한 ViT가 객체 관련 영역에 더 선명하고 국소화된 초점을 보이면서 무관한(배경) 특징으로부터의 방해를 줄여 더 신뢰할 수 있는 모델을 가능하게 함을 확인한다. 코드는 https://github.com/prdvanderwal/inhibited-self-attention 에서 공개한다.
Evaluating the Performance of TAAF for image classification models
FewVS: A Vision-Semantics Integration Framework for Few-Shot Image Classification
Implementing Lightweight Intrusion Detection System on Resource Constrained Devices
Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification
Evolving Efficient CNN Based Model for Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.