PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address. KERYN HEADLINES Weekly, week 30 of 2024 Retrospective Covers 16 July 2024 11:00 to 23 July 2024 11:00 UTC Web: https://keryn.dev/headlines/weekly/2024-W30/ TOP DEVELOPMENTS [1] SolarWinds fixes 8 critical bugs in access rights audit software BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/solarwinds-fixes-8-critical-bugs-in-access-rights-audit-software [2] Breaking Instruction Hierarchy in OpenAI's gpt-4o-mini Simon Willison · Research · https://simonwillison.net/2024/Jul/22/breaking-instruction-hierarchy [3] Critical Cisco bug lets hackers add root users on SEG devices BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/critical-cisco-bug-lets-hackers-add-root-users-on-seg-devices [4] Researcher finds flaw in a16z website that exposed some company data TechCrunch: Security · Research · https://techcrunch.com/2024/07/18/researcher-finds-flaw-in-a16z-website-that-exposed-some-company-data SAST [5] SNIP: Speculative Execution and Non-Interference Preservation for Compiler Transformations arXiv · Research · https://arxiv.org/abs/2407.15080 [6] SCoPE: Evaluating LLMs for Software Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2407.14372 [7] Your control tower to secure code across GitHub, GitLab, and Azure Repos Wiz · Analysis · https://wiz.io/blog/wiz-code-unify-security-across-github-gitlab-and-azure-repos SCA [8] Chainguard joins Coalition for Secure AI with OpenAI, Google, Anthropic CoSAI · Analysis · https://coalitionforsecureai.org/chainguard-joins-coalition-for-secure-ai-with-openai-google-anthropic [9] Intel Welcomes the Coalition for Secure AI CoSAI · Analysis · https://coalitionforsecureai.org/intel-welcomes-the-coalition-for-secure-ai [10] SocGholish Malware Exploits BOINC Project for Covert Cyberattacks The Hacker News · Analysis · https://thehackernews.com/2024/07/socgholish-malware-exploits-boinc.html DAST [11] Virtual Reality and Augmented Reality Security: A Reconnaissance and Vulnerability Assessment Approach arXiv · Research · https://arxiv.org/abs/2407.15984 [12] Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN arXiv · Research · https://arxiv.org/abs/2407.15656 [13] FuzzTheREST: An Intelligent Automated Black-box RESTful API Fuzzer arXiv · Research · https://arxiv.org/abs/2407.14361 [14] Bridging the Gap: A Survey and Classification of Research-Informed Ethical Hacking Tools arXiv · Research · https://arxiv.org/abs/2407.14255 REMEDIATION [15] Cisco SSM On-Prem bug lets hackers change any user's password BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/cisco-ssm-on-prem-bug-lets-hackers-change-any-users-password [16] Critical Apache HugeGraph Vulnerability Under Attack - Patch ASAP The Hacker News · Analysis · https://thehackernews.com/2024/07/critical-apache-hugegraph-vulnerability.html [17] Microsoft finally fixes Outlook alerts bug caused by December updates BleepingComputer · Analysis · https://bleepingcomputer.com/news/microsoft/microsoft-finally-fixes-outlook-alerts-bug-caused-by-december-updates [18] Cybercriminals Exploit CrowdStrike Update Mishap to Distribute Remcos RAT Malware The Hacker News · Analysis · https://thehackernews.com/2024/07/cybercriminals-exploit-crowdstrike.html TRUST [19] The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis arXiv · Research · https://arxiv.org/abs/2408.02379 [20] Open Problems in Technical AI Governance arXiv · Research · https://arxiv.org/abs/2407.14981 [21] From Principles to Practices: Lessons Learned from Applying Partnership on AI's (PAI) Synthetic Media Framework to 11 Use Cases arXiv · Research · https://arxiv.org/abs/2407.13025 [22] Introducing the Coalition for Secure AI, an OASIS Open Project CoSAI · Announcement · https://coalitionforsecureai.org/introducing-the-coalition-for-secure-ai-an-oasis-open-project MODELS [23] PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing arXiv · Research · https://arxiv.org/abs/2407.16318 [24] Reasoning as a Weapon: Adaptive Dual-Path Jailbreak Attack on Large Language Models arXiv · Research · https://arxiv.org/abs/2407.16205 [25] Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs arXiv · Research · https://arxiv.org/abs/2407.15549 [26] Failures to Find Transferable Image Jailbreaks Between Vision-Language Models arXiv · Research · https://arxiv.org/abs/2407.15211 AI SECURITY [27] Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts arXiv · Research · https://arxiv.org/abs/2407.15050 [28] Prompt injection sample against gpt-4o-mini Simon Willison · Analysis · https://simonwillison.net/2024/Jul/19/prompt-injection-gpt-4o-mini ADVISORIES IN THIS WINDOW 20 PyPI advisories · 1 critical · 6 high · 9 moderate · 4 low 16 Maven advisories · 1 critical · 8 high · 7 moderate 15 npm advisories · 14 critical · 1 moderate 11 Go advisories · 1 critical · 7 high · 3 moderate 8 Packagist advisories · 2 high · 5 moderate · 1 low 4 NuGet advisories · 1 critical · 1 high · 1 moderate · 1 low 3 crates.io advisories · 1 high · 2 moderate 3 Multi-ecosystem advisories · 1 high · 2 moderate 1 RubyGems advisory · 1 moderate All advisories: https://keryn.dev/headlines/advisories/ Titles, links and short excerpts only; every item links to its source. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.