1.4.A.3Adversaries can craft prompts that extract secure or sensitive information from LLMs. Secure or sensitive information in LLMs can come from user input and the large data sets used to train LLMs.Learning objective: Explain how adversaries use AI-powered tools to augment cyberattacks.
3.5.B.2Threat detection teams are creating AI algorithms to analyze large amounts of data and classify the data patterns as malicious or normal.Learning objective: Explain how organizations can leverage artificial intelligence (AI) to enhance threat detection and response.
5.6.A.1Devices track and log when data are accessed and by whom. The process of recording and monitoring user activities is called accounting. Analysis of these logs can reveal malicious activity when an adversary attempts to access,…Learning objective: Explain how to detect attacks on data.
AP Networking alignment
4.1.A.3When confidentiality is compromised, systems are vulnerable to having sensitive data exposed or stolen. A breach of confidentiality can be identified by: • unauthorized access • network traffic showing exfiltration of…Learning objective: Identify evidence of compromised confidentiality, integrity, or availability.
4.5.B.4Security controls to limit the impact of unauthorized access include: • enforcing strong password policies and account lockout settings • applying the principle of least privilege • implementing segmentation to restrict access…Learning objective: Determine appropriate security controls to limit the impacts of common threats and vulnerabilities in a managed network.
4.5.C.3IDS and IPS logs and alerts can be reviewed for indicators of security threats that suggest potential unauthorized access or malicious activity. These can include: • repeated failed login attempts • access attempts outside of…Learning objective: Identify indicators in intrusion detection system (IDS) or intrusion prevention system (IPS) logs that may suggest potential threats or network issues.