.png "back to home page")
Yikes. Bit of work to do on the classifier there, eh? Appending strings to malware help them slide by Cylance. I wonder how much of this comes down to losing insight into how a model is making its decisions. I’m sure they’ll fix this but it’s an interesting bypass. https://t.co/DB07Qpj7nn
— Patrick Gray (@riskybusiness) July 18, 2019
Researchers have uncovered a global bypass attack for tricking Cylance's AI-based detection engine into thinking WannaCry, SamSam and other known malicious files are benign. https://t.co/oBjypNAA4g
— Kim Zetter (@KimZetter) July 18, 2019
The researchers, from @SkylightCyber, have described the technical details around their reverse-engineering of the Cylance AI as well as the hack in a blog post: https://t.co/IwdWJtFafH
— Kim Zetter (@KimZetter) July 18, 2019
The researchers, from @SkylightCyber, have described the technical details around their reverse-engineering of the Cylance AI as well as the hack in a blog post: https://t.co/IwdWJtFafH
— Kim Zetter (@KimZetter) July 18, 2019
Reference to what I’m talking about here: https://t.co/LOGYuMIW0N
— Dave Kennedy (ReL1K) (@HackingDave) July 19, 2019
AIベースのEPPをBypassする手法。細工した文字列をMimikatzに付与する事で、CylanceをBypassできたとのこと。同製品のログには信頼度スコアが出力されており、これを観察してCylanceの挙動を分析し、分類結果を狂わせる文字列を見つけたとの事。面白そうなので詳しく読む。https://t.co/CHk6L8fvzx
— Isao Takaesu (@bbr_bbq) July 19, 2019
Skylight Cyber | Cylance, I Kill You! https://t.co/VR2bL9iIVs
— Masafumi Negishi (@MasafumiNegishi) July 19, 2019
Researchers have uncovered a global bypass attack for tricking Cylance's AI-based detection engine into thinking WannaCry, SamSam and other known malicious files are benign. https://t.co/oBjypNAA4g
— Kim Zetter (@KimZetter) July 18, 2019
Researchers were able to trick @cylanceinc AI-based antivirus protection by appending strings from an online gaming gaming that caused known malware, like WannaCry, to be seen as benign#AI #ML #antivirus #wannacry #infosec #cybersecurity #researchhttps://t.co/MZeKLRkUzX pic.twitter.com/dzv9G4Ef3x
— SecurityTrails (@securitytrails) July 19, 2019
Motherboard Researchers Easily Trick Cylance's AI-Based Antivirus Into Thinking Malware Is 'Goodware': By taking strings from an online gaming program and appending them to malicious files, researchers were able to trick… https://t.co/KenRu4EHOS #AI #Hacking Via @motherboard pic.twitter.com/xZiFmA6qvw
— Bradley Jon Eaglefeather (@bjeaglefeather) July 19, 2019
"They're all good malware, Brant."https://t.co/tn4l6b9tuh
— infosecsherpa (@InfoSecSherpa) July 19, 2019
AI 기반의 안티 바이러스에게 악성 코드가 '굿웨어'라고 생각하게 하기 https://t.co/buSjIqEpP4
— editoy (@editoy) July 20, 2019
• 즉, 특정 모델의 작동 방식과 의사 결정에 사용되는 기능 유형을 진정으로 이해할 수 있다면 일관성있게 속일 수 있는 보편적 우회를 만들 가능성이 있습니다.
Researchers Easily Trick Cylance's AI-Based Antivirus Into Thinking via @rightrelevance thanks @mark_riedl https://t.co/yoMQUlfUGN
— Bojan Tunguz (@tunguz) July 19, 2019
“Their crime is not that they coded AI poorly. Their crime is calling what they did AI."https://t.co/owuCptSBra
— Motherboard (@motherboard) July 18, 2019
By taking strings from an online gaming program and appending them to malicious files, researchers were able to trick Cylance’s AI-based antivirus engine into thinking programs like WannaCry and other malware are benign.https://t.co/3ibMNrbOPi#Malware #Cybersecurity #Tech
— US Cybersecurity Mag. (@USCyberMag) July 19, 2019
Researchers Easily Trick Cylance's AI-Based Antivirus Into Thinking Malware Is 'Goodware' -
— malwareport (@malwaresick) July 20, 2019
#Cybersecurity #malware https://t.co/7CIpAbksFa