Skip to content
SSL and internet security news

Informations about SSL certificates and networks security

Category: machine learning

Auto Added by WPeMatico

AIs as Trusted Third Parties

Posted on March 28, 2025 By infossl
academic papers, AI, cryptography, machine learning, Security technology, trust, Uncategorized

This is a truly fascinating paper: “Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography.” The basic idea is that AIs can act as trusted third parties: Abstract: We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private … Read More “AIs as Trusted Third Parties” »

A Taxonomy of Adversarial Machine Learning Attacks and Mitigations

Posted on March 27, 2025 By infossl
machine learning, nist, Security technology, taxonomies, Uncategorized

NIST just released a comprehensive taxonomy of adversarial machine learning attacks and countermeasures. Powered by WPeMatico

Using LLMs to Unredact Text

Posted on March 11, 2024 By infossl
LLM, machine learning, Security technology, Uncategorized

Initial results in using LLMs to unredact text based on the size of the individual-word redaction rectangles. This feels like something that a specialized ML system could be trained on. Powered by WPeMatico

Poisoning AI Models

Posted on January 24, 2024 By infossl
academic papers, artificial intelligence, LLM, machine learning, Security technology, threat models, Uncategorized

New research into poisoning AI models: The researchers first trained the AI models using supervised learning and then used additional “safety training” methods, including more supervised learning, reinforcement learning, and adversarial training. After this, they checked if the AI still had hidden behaviors. They found that with specific prompts, the AI could still generate exploitable … Read More “Poisoning AI Models” »

Extracting GPT’s Training Data

Posted on November 30, 2023 By infossl
academic papers, artificial intelligence, ChatGPT, cyberattack, machine learning, Security technology, Uncategorized

This is clever: The actual attack is kind of silly. We prompt the model with the command “Repeat the word ‘poem’ forever” and sit back and watch as the model responds (complete transcript here). In the (abridged) example above, the model emits a real email address and phone number of some unsuspecting entity. This happens … Read More “Extracting GPT’s Training Data” »

Bots Are Better than Humans at Solving CAPTCHAs

Posted on August 18, 2023 By infossl
academic papers, captchas, machine learning, Security technology, Uncategorized

Interesting research: “An Empirical Study & Evaluation of Modern CAPTCHAs“: Abstract: For nearly two decades, CAPTCHAS have been widely used as a means of protection against bots. Throughout the years, as their use grew, techniques to defeat or bypass CAPTCHAS have continued to improve. Meanwhile, CAPTCHAS have also evolved in terms of sophistication and diversity, … Read More “Bots Are Better than Humans at Solving CAPTCHAs” »

Using Machine Learning to Detect Keystrokes

Posted on August 9, 2023 By infossl
machine learning, Security technology, side-channel attacks, smartphones, Uncategorized

Researchers have trained a ML model to detect keystrokes by sound with 95% accuracy. “A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards” Abstract: With recent developments in deep learning, the ubiquity of microphones and the rise in online services via personal devices, acoustic side channel attacks present a greater threat to keyboards than … Read More “Using Machine Learning to Detect Keystrokes” »

Indirect Instruction Injection in Multi-Modal LLMs

Posted on July 28, 2023 By infossl
academic papers, artificial intelligence, LLM, machine learning, Security technology, Uncategorized

Interesting research: “(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs“: Abstract: We demonstrate how images and sounds can be used for indirect prompt and instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding to the prompt and blends it into an image or audio recording. When the user asks … Read More “Indirect Instruction Injection in Multi-Modal LLMs” »

Security Risks of AI

Posted on April 27, 2023 By infossl
artificial intelligence, cybersecurity, machine learning, reports, risks, Security technology, Uncategorized

Stanford and Georgetown have a new report on the security risks of AI—particularly adversarial machine learning—based on a workshop they held on the topic. Jim Dempsey, one of the workshop organizers, wrote a blog post on the report: As a first step, our report recommends the inclusion of AI security concerns within the cybersecurity programs … Read More “Security Risks of AI” »

Using LLMs to Create Bioweapons

Posted on April 18, 2023 By infossl
academic papers, artificial intelligence, biological warfare, machine learning, Security technology, Uncategorized

I’m not sure there are good ways to build guardrails to prevent this sort of thing: There is growing concern regarding the potential misuse of molecular machine learning models for harmful purposes. Specifically, the dual-use application of models for predicting cytotoxicity18 to create new poisons or employing AlphaFold2 to develop novel bioweapons has raised alarm. … Read More “Using LLMs to Create Bioweapons” »

Posts pagination

1 2 3 Next
fr_FR

Recent Posts

  • Chinese AI Submersible
  • Fake Student Fraud in Community Colleges
  • Another Move in the Deepfake Creation/Detection Arms Race
  • Friday Squid Blogging: Pyjama Squid
  • Privacy for Agentic AI

Tags

academicpapers airgaps android anonymity authentication borders cars cellphones censorship control courts crime cryptanalysis cryptography cryptowars deanonymization edwardsnowden encryption fbi fear geolocation guardian hacking intelligence ios jamming keyescrow lies malware medicine nationalsecuritypolicy nsa pointofsale printers privacy rc4 retail secrecy sidechannelattacks socialmedia squid surveillance tracking tradecraft whistleblowers

Categories

  • 3dprinters
  • 911
  • A Hacker's Mind
  • academic
  • academic papers
  • academicpapers
  • accountability
  • aclu
  • activism
  • adobe
  • advanced persistent threats
  • advancedpersistentthreats
  • adware
  • aes
  • AI
  • air travel
  • airgaps
  • airtravel
  • al Qaeda
  • alarms
  • algorithms
  • alqaeda
  • amazon
  • android
  • anonymity
  • Anonymous
  • antivirus
  • apache
  • apple
  • Applied Cryptography
  • appliedcryptography
  • artificial intelligence
  • artificialintelligence
  • assassinations
  • atms
  • att
  • attribution
  • audio
  • auditing
  • australia
  • authentication
  • authorization
  • automation
  • backdoors
  • backups
  • banking
  • baserate
  • behavioraldetection
  • Beyond Fear
  • beyondfear
  • bgp
  • biological warfare
  • biologicalwarfare
  • biometrics
  • bios
  • bitcoin
  • BitLocker
  • blackberry
  • blackmail
  • blockchain
  • bluetooth
  • bombs
  • books
  • borders
  • botnets
  • brazil
  • breaches
  • bribes
  • browsers
  • business of security
  • businessofsecurity
  • CALEA
  • cameras
  • camouflage
  • canada
  • captchas
  • cars
  • casinos
  • cell phones
  • cellphones
  • censorship
  • certificates
  • certifications
  • ch2ke
  • chatbots
  • ChatGPT
  • cheating
  • chelseamanning
  • chess
  • child pornography
  • childpornography
  • children
  • china
  • chipandpin
  • chrome
  • Chrome OS
  • cia
  • cisco
  • Citizen Lab
  • citizenlab
  • cloning
  • cloud computing
  • cloudcomputing
  • co3systems
  • coastguard
  • colombia
  • complexity
  • compliance
  • computer security
  • computersecurity
  • concealment
  • conferences
  • cons
  • consumerization
  • contests
  • control
  • cookies
  • cooperation
  • copyright
  • costbenefitanalysis
  • courts
  • cover-ups
  • coverups
  • COVID-19
  • covid19
  • cracking
  • credentials
  • credit cards
  • creditcards
  • crime
  • cross-site scripting
  • crowdsourcing
  • cryptanalysis
  • crypto wars
  • cryptocurrency
  • cryptography
  • cryptome
  • cryptowars
  • cuba
  • cyberattack
  • cybercrime
  • cyberespionage
  • cybersecurity
  • cyberterrorism
  • cyberwar
  • cyberweapons
  • dark web
  • darkweb
  • darpa
  • Data and Goliath
  • data breaches
  • data collection
  • data destruction
  • data loss
  • data mining
  • data privacy
  • data protection
  • dataandgoliath
  • databases
  • databreaches
  • datacollection
  • datadestruction
  • dataloss
  • datamining
  • dataprotection
  • dataretention
  • de-anonymization
  • dea
  • deaddrops
  • deanonymization
  • debates
  • deception
  • deep fake
  • deepfake
  • defense
  • democracy
  • deniability
  • denial of service
  • denialofservice
  • Department of Defense
  • departmentofdefense
  • dhs
  • disclosure
  • disguise
  • disinformation
  • dmca
  • dna
  • dns
  • doghouse
  • domain names
  • doxing
  • drm
  • drones
  • drug trade
  • drugtrade
  • e-mail
  • eavesdropping
  • ebay
  • ebooks
  • economics of security
  • economicsofsecurity
  • Edward Snowden
  • edwardsnowden
  • eff
  • egypt
  • email
  • embedded systems
  • embeddedsystems
  • employment
  • encryption
  • enigma
  • EPIC
  • epidemiology
  • espionage
  • essays
  • estonia
  • ethics
  • eu
  • EULA
  • exploits
  • externalities
  • extortion
  • face recognition
  • facebook
  • facerecognition
  • fake news
  • fakenews
  • false positives
  • falsenegatives
  • falsepositives
  • fbi
  • fear
  • feudalsecurity
  • filesharing
  • filtering
  • finance
  • fingerprints
  • firefox
  • firewall
  • firmware
  • fisa
  • foia
  • forensics
  • forgery
  • Fortuna
  • france
  • fraud
  • fsecure
  • ftc
  • g7
  • gambling
  • game theory
  • games
  • gametheory
  • gaming consoles
  • gchq
  • gdpr
  • generations
  • geolocation
  • Georgia
  • germany
  • gmail
  • google
  • googleglass
  • gps
  • Greece
  • Guardian
  • guns
  • hackback
  • hacking
  • hardware
  • hashes
  • healthcare
  • Hezbollah
  • history of computing
  • history of cryptography
  • history of security
  • historyofcomputing
  • historyofcryptography
  • historyofsecurity
  • hoaxes
  • homelandsecurity
  • homomorphic encryption
  • hotels
  • hp
  • https
  • human rights
  • humor
  • ibm
  • ics
  • idcards
  • identification
  • identity theft
  • identitytheft
  • impersonation
  • implants
  • incentives
  • incident response
  • incidentresponse
  • india
  • infrastructure
  • inrupt
  • insiders
  • insurance
  • intel
  • intelligence
  • internet
  • Internet and society
  • Internet of Things
  • internetandsociety
  • internetexplorer
  • internetofthings
  • interviews
  • intrusion detection
  • ios
  • iphone
  • iran
  • iraq
  • ireland
  • irs
  • isis
  • isps
  • israel
  • italy
  • jamming
  • japan
  • Juniper
  • kaspersky
  • kazakhstan
  • key logging
  • keyescrow
  • keylogging
  • keys
  • kidnapping
  • killswitch
  • law enforcement
  • lawenforcement
  • laws
  • leaks
  • lebanon
  • lenovo
  • Liars and Outliers
  • liarsandoutliers
  • lies
  • linkedin
  • linux
  • LLM
  • locks
  • loopholes
  • lotteries
  • machine learning
  • machinelearning
  • mail
  • malware
  • man-in-the-middle attacks
  • maninthemiddleattacks
  • marketing
  • mcafee
  • md5
  • medicine
  • Meta
  • metadata
  • microsoft
  • military
  • mitigation
  • monoculture
  • movieplotthreats
  • mozilla
  • music
  • national security policy
  • nationalism
  • nationalsecurityletters
  • nationalsecuritypolicy
  • natural security
  • naturalsecurity
  • networksecurity
  • New York Times
  • Nigeria
  • nist
  • no-fly list
  • Non classé
  • noncomputer hacks
  • North Korea
  • northkorea
  • norway
  • nsa
  • obscurity
  • onetimepads
  • open source
  • opensource
  • operating systems
  • operatingsystems
  • operational security
  • operationalsecurity
  • overreactions
  • pakistan
  • Password Safe
  • passwords
  • passwordsafe
  • patching
  • patents
  • patriotact
  • paypal
  • penetration testing
  • penetrationtesting
  • pgp
  • phishing
  • phones
  • photos
  • physical security
  • physicalsecurity
  • pins
  • plagiarism
  • point of sale
  • pointofsale
  • police
  • policy
  • pornography
  • power
  • press
  • printers
  • prison escapes
  • prisons
  • privacy
  • privilege escalation
  • programming
  • propaganda
  • protocols
  • proxies
  • pseudonymity
  • psychology of security
  • psychologyofsecurity
  • public interest
  • public transit
  • publicinterest
  • publictransit
  • qatar
  • QR codes
  • quantum computing
  • quantum cryptography
  • quantumcomputing
  • quantumcryptography
  • radio
  • random numbers
  • randomnumbers
  • ransomware
  • redaction
  • regulation
  • replayattacks
  • reports
  • reputation
  • resilience
  • Resilient Systems
  • resilientsystems
  • restaurants
  • retail
  • reverse engineering
  • reverseengineering
  • rfid
  • risk assessment
  • riskassessment
  • risks
  • robbery
  • robotics
  • rootkits
  • rsa
  • russia
  • sabotage
  • Safari
  • safes
  • samsung
  • saudiarabia
  • scada
  • scams
  • scanners
  • Schneier news
  • Schneier on Security (book)
  • schneiernews
  • schneierslaw
  • schools
  • sciencefiction
  • search engines
  • searches
  • secrecy
  • secretsharing
  • security analysis
  • security conferences
  • security education
  • security engineering
  • security standards
  • Security technology
  • security theater
  • security tokens
  • securityanalysis
  • securityawareness
  • securityconferences
  • securityeducation
  • securityengineering
  • securitymindset
  • securitymonitoring
  • securitypolicies
  • securityquestions
  • securitystandards
  • securitytheater
  • securitytokens
  • sensors
  • sha1
  • side-channel attacks
  • sidechannelattacks
  • signal
  • signatures
  • SIM cards
  • simcards
  • skimmers
  • skype
  • smart cards
  • smartcards
  • smartphones
  • sms
  • smuggling
  • snake oil
  • snakeoil
  • social engineering
  • social media
  • socialengineering
  • socialmedia
  • societalsecurity
  • software
  • software liability
  • softwareliability
  • sony
  • southkorea
  • spain
  • spam
  • spoofing
  • sports
  • spyware
  • SQL injection
  • sqlinjection
  • squid
  • ss7
  • ssh
  • ssl
  • stalking
  • steganography
  • stuxnet
  • supply chain
  • supplychain
  • surveillance
  • sweden
  • switzerland
  • symantec
  • syria
  • T-Mobile
  • Taiwan
  • tamper detection
  • tamperdetection
  • taxonomies
  • TED
  • telecom
  • telegram
  • television
  • tempest
  • terms of service
  • termsofservice
  • terrorism
  • Thailand
  • theft
  • threat models
  • threatalerts
  • threatmodels
  • tls
  • tor
  • torrents
  • torture
  • tpm
  • tracing
  • tracking
  • tradecraft
  • traffic analysis
  • trafficanalysis
  • transparency
  • transportation
  • treaties
  • trust
  • tsa
  • turkey
  • twitter
  • two-factor authentication
  • twofactorauthentication
  • twofish
  • uae
  • uber
  • uk
  • ukraine
  • un
  • Uncategorized
  • undercover
  • unitedarabemirates
  • usability
  • usb
  • usps
  • utilities
  • uzbekistan
  • verisign
  • verizon
  • video
  • videoconferencing
  • videos
  • violence
  • voice recognition
  • voicerecognition
  • voip
  • voting
  • vpn
  • vulnerabilities
  • war
  • war on the unexpected
  • warontheunexpected
  • watchlists
  • weapons
  • web
  • web privacy
  • webprivacy
  • whatsapp
  • whistleblowers
  • Wi-Fi
  • wifi
  • wikileaks
  • windows
  • wireless
  • yahoo
  • zero-day
  • zeroday

Archives

  • May 2025
  • April 2025
  • March 2025
  • February 2025
  • September 2024
  • August 2024
  • July 2024
  • June 2024
  • May 2024
  • April 2024
  • March 2024
  • February 2024
  • January 2024
  • December 2023
  • November 2023
  • October 2023
  • September 2023
  • August 2023
  • July 2023
  • June 2023
  • May 2023
  • April 2023
  • March 2023
  • February 2023
  • January 2023
  • December 2022
  • November 2022
  • October 2022
  • September 2022
  • August 2022
  • July 2022
  • June 2022
  • May 2022
  • April 2022
  • March 2022
  • February 2022
  • January 2022
  • December 2021
  • November 2021
  • October 2021
  • September 2021
  • August 2021
  • July 2021
  • June 2021
  • May 2021
  • April 2021
  • March 2021
  • February 2021
  • August 2020
  • July 2020
  • June 2020
  • May 2020
  • April 2020
  • March 2020
  • February 2020
  • January 2020
  • December 2019
  • November 2019
  • October 2019
  • September 2019
  • August 2019
  • July 2019
  • June 2019
  • May 2019
  • April 2019
  • March 2019
  • February 2019
  • January 2019
  • December 2018
  • November 2018
  • October 2018
  • September 2018
  • August 2018
  • July 2018
  • June 2018
  • May 2018
  • April 2018
  • March 2018
  • February 2018
  • January 2018
  • December 2017
  • November 2017
  • October 2017
  • September 2017
  • August 2017
  • July 2017
  • June 2017
  • May 2017
  • April 2017
  • March 2017
  • February 2017
  • January 2017
  • December 2016
  • November 2016
  • October 2016
  • September 2016
  • August 2016
  • March 2015
  • February 2015
  • January 2015
  • December 2014
  • November 2014
  • October 2014

Copyright © 2025 SSL and internet security news.

Theme: Oceanly by ScriptsTown