Adversarial attacks on machine learning (ML) models are growing in intensity, frequency and class with more enterprises admitting they’ve experienced an AI-related security incident.
AI’s pervasive adoption is resulting in a rapidly expanding threat surface that every one enterprises struggle to maintain up with. A recent Gartner survey on AI adoption shows that 73% of enterprises have tons of or hundreds of AI models deployed.
HiddenLayer’s earlier study found that 77% of the businesses identified AI-related breaches, and the remaining corporations were uncertain whether their AI models had been attacked. Two in five organizations had an AI privacy breach or security incident of which 1 in 4 were malicious attacks.
A growing threat of adversarial attacks
With AI’s growing influence across industries, malicious attackers proceed to sharpen their tradecraft to use ML models’ growing base of vulnerabilities as the variability and volume of threat surfaces expand.
Adversarial attacks on ML models look to use gaps by intentionally attempting to redirect the model with inputs, corrupted data, jailbreak prompts and by hiding malicious commands in images loaded back right into a model for evaluation. Attackers fine-tune adversarial attacks to make models deliver false predictions and classifications, producing the unsuitable output.
VentureBeat contributor Ben Dickson explains how adversarial attacks work, the various forms they take and the history of research on this area.
Gartner also found that 41% of organizations reported experiencing some type of AI security incident, including adversarial attacks targeting ML models. Of those reported incidents, 60% were data compromises by an internal party, while 27% were malicious attacks on the organization’s AI infrastructure. Thirty percent of all AI cyberattacks will leverage training-data poisoning, AI model theft or adversarial samples to attack AI-powered systems.
Adversarial ML attacks on network security are growing
Disrupting entire networks with adversarial ML attacks is the stealth attack strategy nation-states are betting on to disrupt their adversaries’ infrastructure, which may have a cascading effect across supply chains. The 2024 Annual Threat Assessment of the U.S. Intelligence Community provides a sobering have a look at how necessary it’s to guard networks from adversarial ML model attacks and why businesses need to contemplate higher securing their private networks against adversarial ML attacks.
A recent study highlighted how the growing complexity of network environments demands more sophisticated ML techniques, creating recent vulnerabilities for attackers to use. Researchers are seeing that the specter of adversarial attacks on ML in network security is reaching epidemic levels.
The quickly accelerating variety of connected devices and the proliferation of knowledge put enterprises into an arms race with malicious attackers, many financed by nation-states searching for to manage global networks for political and financial gain. It’s now not a matter of if a company will face an adversarial attack but when. The battle against adversarial attacks is ongoing, but organizations can gain the upper hand with the precise strategies and tools.
Cisco, Cradlepoint( a subsidiary of Ericsson), DarkTrace, Fortinet, Palo Alto Networks, and other leading cybersecurity vendors have deep expertise in AI and ML to detect network threats and protect network infrastructure. Each is taking a singular approach to solving this challenge. VentureBeat’s evaluation of Cisco’s and Cradlepoint’s latest developments indicates how briskly vendors address this and other network and model security threats. Cisco’s recent acquisition of Robust Intelligence accentuates how necessary protecting ML models is to the network giant.
Understanding adversarial attacks
Adversarial attacks exploit weaknesses in the info’s integrity and the ML model’s robustness. According to NIST’s Artificial Intelligence Risk Management Framework, these attacks introduce vulnerabilities, exposing systems to adversarial exploitation.
There are several forms of adversarial attacks:
Data Poisoning: Attackers introduce malicious data right into a model’s training set to degrade performance or control predictions. According to a Gartner report from 2023, nearly 30% of AI-enabled organizations, particularly those in finance and healthcare, have experienced such attacks. Backdoor attacks embed specific triggers in training data, causing models to behave incorrectly when these triggers appear in real-world inputs. A 2023 MIT study highlights the growing risk of such attacks as AI adoption grows, making defense strategies comparable to adversarial training increasingly necessary.
Evasion Attacks: These attacks alter input data to mispredict. Slight image distortions can confuse models into misclassified objects. A well-liked evasion method, the Fast Gradient Sign Method (FGSM) uses adversarial noise to trick models. Evasion attacks within the autonomous vehicle industry have caused safety concerns, with altered stop signs misinterpreted as yield signs. A 2019 study found that a small sticker on a stop sign misled a self-driving automotive into considering it was a speed limit sign. Tencent’s Keen Security Lab used road stickers to trick a Tesla Model S’s autopilot system. These stickers steered the automotive into the unsuitable lane, showing how small rigorously crafted input changes could be dangerous. Adversarial attacks on critical systems like autonomous vehicles are real-world threats.
Model Inversion: Allows adversaries to infer sensitive data from a model’s outputs, posing significant risks when trained on confidential data like health or financial records. Hackers query the model and use the responses to reverse-engineer training data. In 2023, Gartner warned, “The misuse of model inversion can result in significant privacy violations, especially in healthcare and financial sectors, where adversaries can extract patient or customer information from AI systems.”
Model Stealing: Repeated API queries are used to copy model functionality. These queries help the attacker create a surrogate model that behaves like the unique. AI Security states, “AI models are sometimes targeted through API queries to reverse-engineer their functionality, posing significant risks to proprietary systems, especially in sectors like finance, healthcare, and autonomous vehicles.” These attacks are increasing as AI is used more, raising concerns about IP and trade secrets in AI models.
Recognizing the weak points in your AI systems
Securing ML models against adversarial attacks requires understanding the vulnerabilities in AI systems. Key areas of focus need to incorporate:
Data Poisoning and Bias Attacks: Attackers goal AI systems by injecting biased or malicious data, compromising model integrity. Healthcare, finance, manufacturing and autonomous vehicle industries have all experienced these attacks recently. The 2024 NIST report warns that weak data governance amplifies these risks. Gartner notes that adversarial training and robust data controls can boost AI resilience by as much as 30%. Implementing secure data pipelines and constant validation is important to protecting critical models.
Model Integrity and Adversarial Training: Machine learning models could be manipulated without adversarial training. Adversarial training uses antagonistic examples and significantly strengthens a model’s defenses. Researchers say adversarial training improves robustness but requires longer training times and should trade accuracy for resilience. Although flawed, it’s a necessary defense against adversarial attacks. Researchers have also found that poor machine identity management in hybrid cloud environments increases the danger of adversarial attacks on machine learning models.
API Vulnerabilities: Model-stealing and other adversarial attacks are highly effective against public APIs and are essential for obtaining AI model outputs. Many businesses are vulnerable to exploitation because they lack strong API security, as was mentioned at BlackHat 2022. Vendors, including Checkmarx and Traceable AI, are automating API discovery and ending malicious bots to mitigate these risks. API security should be strengthened to preserve the integrity of AI models and safeguard sensitive data.
Best practices for securing ML models
Implementing the next best practices can significantly reduce the risks posed by adversarial attacks:
Robust Data Management and Model Management: NIST recommends strict data sanitization and filtering to stop data poisoning in machine learning models. Avoiding malicious data integration requires regular governance reviews of third-party data sources. ML models must even be secured by tracking model versions, monitoring production performance and implementing automated, secured updates. BlackHat 2022 researchers stressed the necessity for continuous monitoring and updates to secure software supply chains by protecting machine learning models. Organizations can improve AI system security and reliability through robust data and model management.
Adversarial Training: ML models are strengthened by adversarial examples created using the Fast Gradient Sign Method (FGSM). FGSM adjusts input data by small amounts to extend model errors, helping models recognize and resist attacks. According to researchers, this method can increase model resilience by 30%. Researchers write that “adversarial training is some of the effective methods for improving model robustness against sophisticated threats.”
Homomorphic Encryption and Secure Access: When safeguarding data in machine learning, particularly in sensitive fields like healthcare and finance, homomorphic encryption provides robust protection by enabling computations on encrypted data without exposure. EY states, “Homomorphic encryption is a game-changer for sectors that require high levels of privacy, because it allows secure data processing without compromising confidentiality.” Combining this with distant browser isolation further reduces attack surfaces ensuring that managed and unmanaged devices are protected through secure access protocols.
API Security: Public-facing APIs should be secured to stop model-stealing and protect sensitive data. BlackHat 2022 noted that cybercriminals increasingly use API vulnerabilities to breach enterprise tech stacks and software supply chains. AI-driven insights like network traffic anomaly evaluation help detect vulnerabilities in real time and strengthen defenses. API security can reduce a company’s attack surface and protect AI models from adversaries.
Regular Model Audits: Periodic audits are crucial for detecting vulnerabilities and addressing data drift in machine learning models. Regular testing for adversarial examples ensures models remain robust against evolving threats. Researchers note that “audits improve security and resilience in dynamic environments.” Gartner’s recent report on securing AI emphasizes that consistent governance reviews and monitoring data pipelines are essential for maintaining model integrity and stopping adversarial manipulation. These practices safeguard long-term security and adaptableness.
Technology solutions to secure ML models
Several technologies and techniques are proving effective in defending against adversarial attacks targeting machine learning models:
Differential privacy: This technique protects sensitive data by introducing noise into model outputs without appreciably lowering accuracy. This strategy is especially crucial for sectors like healthcare that value privacy. Differential privacy is a method utilized by Microsoft and IBM amongst other corporations to guard sensitive data of their AI systems.
AI-Powered Secure Access Service Edge (SASE): As enterprises increasingly consolidate networking and security, SASE solutions are gaining widespread adoption. Major vendors competing on this space include Cisco, Ericsson, Fortinet, Palo Alto Networks, VMware and Zscaler. These corporations offer a variety of capabilities to handle the growing need for secure access in distributed and hybrid environments. With Gartner predicting that 80% of organizations will adopt SASE by 2025 this market is ready to expand rapidly.
Ericsson distinguishes itself by integrating 5G-optimized SD-WAN and Zero Trust security, enhanced by acquiring Ericom. This combination enables Ericsson to deliver a cloud-based SASE solution tailored for hybrid workforces and IoT deployments. Its Ericsson NetCloud SASE platform has proven precious in providing AI-powered analytics and real-time threat detection to the network edge. Their platform integrates Zero Trust Network Access (ZTNA), identity-based access control, and encrypted traffic inspection. Ericsson’s cellular intelligence and telemetry data train AI models that aim to enhance troubleshooting assistance. Their AIOps can routinely detect latency, isolate it to a cellular interface, determine the foundation cause as an issue with the cellular signal after which recommend remediation.
Federated Learning with Homomorphic Encryption: Federated learning allows decentralized ML training without sharing raw data, protecting privacy. Computing encrypted data with homomorphic encryption ensures security throughout the method. Google, IBM, Microsoft, and Intel are developing these technologies, especially in healthcare and finance. Google and IBM use these methods to guard data during collaborative AI model training, while Intel uses hardware-accelerated encryption to secure federated learning environments. Data privacy is protected by these innovations for secure, decentralized AI.
Defending against attacks
Given the potential severity of adversarial attacks, including data poisoning, model inversion, and evasion, healthcare and finance are especially vulnerable, as these industries are favorite targets for attackers. By employing techniques including adversarial training, robust data management, and secure API practices, organizations can significantly reduce the risks posed by adversarial attacks. AI-powered SASE, built with cellular-first optimization and AI-driven intelligence has proven effective in defending against attacks on networks.
