As one of many defining applied sciences of this century, synthetic intelligence (AI) appears to witness each day developments with new entrants to the sector, technological breakthroughs, and artistic and revolutionary purposes. The panorama for AI safety shares the identical breakneck tempo with streams of newly proposed laws, novel vulnerability discoveries, and rising menace vectors.
Whereas the pace of change is thrilling, it creates sensible obstacles for enterprise AI adoption. As our Cisco 2024 AI Readiness Index factors out, issues about AI safety are ceaselessly cited by enterprise leaders as a major roadblock to embracing the complete potential of AI of their organizations.
That’s why we’re excited to introduce our inaugural State of AI Safety report. It gives a succinct, easy overview of among the most necessary developments in AI safety from the previous yr, together with traits and predictions for the yr forward. The report additionally shares clear suggestions for organizations seeking to enhance their very own AI safety methods, and highlights among the methods Cisco is investing in a safer future for AI.
Right here’s an outline of what you’ll discover in our first State of AI Safety report:
Evolution of the AI Risk Panorama
The speedy proliferation of AI and AI-enabled applied sciences has launched a large new assault floor that safety leaders are solely starting to deal with.
Danger exists at just about each step throughout the whole AI growth lifecycle; AI property might be immediately compromised by an adversary or discreetly compromised although a vulnerability within the AI provide chain. The State of AI Safety report examines a number of AI-specific assault vectors together with immediate injection assaults, information poisoning, and information extraction assaults. It additionally displays on using AI by adversaries to enhance cyber operations like social engineering, supported by analysis from Cisco Talos.
Trying on the yr forward, cutting-edge developments in AI will undoubtedly introduce new dangers for safety leaders to pay attention to. For instance, the rise of agentic AI which may act autonomously with out fixed human supervision appears ripe for exploitation. However, the scale of social engineering threatens to develop tremendously, exacerbated by highly effective multimodal AI instruments within the incorrect palms.
Key Developments in AI Coverage
The previous yr has seen vital developments in AI coverage, each domestically and internationally.
In america, a fragmented state-by-state strategy has emerged within the absence of federal laws with over 700 AI-related payments launched in 2024 alone. In the meantime, worldwide efforts have led to key developments, such because the UK and Canada’s collaboration on AI security and the European Union’s AI Act, which got here into power in August 2024 to set a precedent for international AI governance.
Early actions in 2025 counsel larger focus in the direction of successfully balancing the necessity for AI safety with accelerating the pace of innovation. Current examples embrace President Trump’s government order and rising help for a pro-innovation surroundings, which aligns effectively with themes from the AI Motion Summit held in Paris in February and the U.Okay.’s current AI Alternatives Motion Plan.
Unique AI Safety Analysis
The Cisco AI safety analysis staff has led and contributed to a number of items of groundbreaking analysis that are highlighted within the State of AI Safety report.
Analysis into algorithmic jailbreaking of enormous language fashions (LLMs) demonstrates how adversaries can bypass mannequin protections with zero human supervision. This method can be utilized to exfiltrate delicate information and disrupt AI providers. Extra lately, the staff explored automated jailbreaking of superior reasoning fashions like DeepSeek R1, to show that even reasoning fashions can nonetheless fall sufferer to conventional jailbreaking strategies.
The staff additionally explores the security and safety dangers of fine-tuning fashions. Whereas fine-tuning is a well-liked technique for bettering the contextual relevance of AI, many are unaware of the inadvertent penalties like mannequin misalignment.
Lastly, the report critiques two items of authentic analysis into poisoning public datasets and extracting coaching information from LLMs. These research make clear how simply—and cost-effectively—a nasty actor can tamper with or exfiltrate information from enterprise AI purposes.
Suggestions for AI Safety
Securing AI techniques requires a proactive and complete strategy.
The State of AI Safety report outlines a number of actionable suggestions, together with managing safety dangers all through the AI lifecycle, implementing robust entry controls, and adopting AI safety requirements such because the NIST AI Danger Administration Framework and MITRE ATLAS matrix. We additionally have a look at how Cisco AI Protection can assist companies adhere to those finest practices and mitigate AI threat from growth to deployment.
Learn the State of AI Safety 2025
Able to learn the complete report? You could find it right here.
We’d love to listen to what you assume. Ask a Query, Remark Beneath, and Keep Linked with Cisco Safe on social!
Cisco Safety Social Channels
Share: