Post Session Report on Universal Acceptance and Multilingual Internet at BIT University under CyberPeace Center of Excellence (CCoE)
11th November 2022 CyberPeace Foundation in association with Universal Acceptance has successfully conducted the workshop on Universal Acceptance and Multilingual Internet for the students and faculties of BIT University under CyberPeace Center of Excellence (CCoE).
CyberPeace Foundation has always been engaged towards the aim of spreading awareness regarding the various developments, avenues, opportunities and threats regarding cyberspace. The same has been the keen principle of the CyberPeace Centre of Excellence setup in collaboration with various esteemed educational institutes. We at CyberPeace Foundation would like to take the collaborations and our efforts to a new height of knowledge and awareness by proposing a workshop on UNIVERSAL ACCEPTANCE AND MULTILINGUAL INTERNET. This workshop was instrumental in providing the academia and research community a wholesome outlook towards the multilingual spectrum of internet including Internationalized domain names and email address Internationalization.
Date –11th November 2022
Time – 10:00 AM to 12:00 PM
Duration – 2 hours
Mode - Online
Audience – Academia and Research Community
Participants Joined- 15
Crowd Classification - Engineering students (1st and 4th year, all streams) and Faculties members
Organizer : Mr. Harish Chowdhary : UA Ambassador
Moderator: Ms. Pooja Tomar, Project coordinator cum trainer
Speakers - Mr. Abdalmonem Galila, Abdalmonem: Vice Chair , Universal Acceptance Steering Group (UASG)and
Mr. Mahesh D Kulkarni Director, Evaris Systems and Former Senior Director, CDAC, Government of India,First session was delivered by Mr. Abdalmonem Galila, Abdalmonem: Vice Chair , Universal Acceptance Steering Group (UASG) “Universal Acceptance( UA) and why UA matters?”
- What is universal acceptance?
- UA is cornerstone to a digitally inclusive internet by ensuring all domain names and email addresses in all languages, script and character length.
- Achieving UA ensures that every person has the ability to navigate the internet.
- Different UA issues were also discussed and explained.
- Tagated systems by the UA and implication were discussed in detail.
Second session was delivered by Mr. Mahesh D Kulkarni, ES Director Evaris on the topic of “IDNs in Indian languages perspective- challenges and solutions”.
- The multilingual diversity of India was focused on and its impact.
- Most students were not aware of what Unicode, IDNS is and their usage.
- Students were briefed by giving real time examples on IDN, Domain name implementation using local language.
- In depth knowledge of and practical exposure of Universal Acceptance and Multilingual Internet has been served to the students.
- Tools and Resources for Domain Name and Domain Languages were explained.
- Languages nuances of Multilingual diversity of India explained with real time facts and figures.
- Given the idea of IDN Email,Homograph attack,Homographic variant with proper real time examples.
- Explained about the security threats and IDNA protocols.
- Given the explanation on ABNF.
- Explained the stages of Universal Acceptance.
Related Blogs
Executive Summary
Mumbai’s Mira–Bhayandar bridge has recently been in the news due to its unusual design. In this context, a photograph is going viral on social media showing a bus seemingly stuck on the bridge. Some users are also sharing the image while claiming that it is from Sonpur subdivision in Bihar. However, an research by the CyberPeace has found that the viral image is not real. The bridge shown in the image is indeed the Mira–Bhayandar bridge, which is under discussion because its design causes it to suddenly narrow from four lanes to two lanes. That said, the bridge is not yet operational, and the viral image showing a bus stuck on it has been created using Artificial Intelligence (AI).
Claim
An Instagram user shared the viral image on January 29, 2026, with the caption:“Are Indian taxpayers happy to see that this is funded by their money?” The link, archive link, and screenshot of the post can be seen below.
Fact Check:
To verify the claim, we first conducted a Google Lens reverse image search. This led us to a post shared by X (formerly Twitter) user Manoj Arora on January 29. While the bridge structure in that image matches the viral photo, no bus is visible in the original post.This raised suspicion that the viral image had been digitally manipulated.
We then ran the viral image through the AI detection tool Hive Moderation, which flagged it as over 99% likely to be AI-generated
Conclusion
The CyberPeace research confirms that while the Mira–Bhayandar bridge is real and has been in the news due to its design, the viral image showing a bus stuck on the bridge has been created using AI tools. Therefore, the image circulating on social media is misleading.
Introduction
Agentic AI systems are autonomous systems that can plan, make decisions, and take actions by interacting with external tools and environments. But they shift the nature of risk by blurring the lines among input, decision, and execution. A conventional model generates an output and stops. An agent takes input, makes plans, invokes tools, updates its state and repeats the cycle. This creates a system where decisions are continuously revised through interaction with external tools and environments, rather than being fixed at the point of input.
This means the attack surface expands in size and becomes more dynamic. Instead of remaining confined to components as in traditional computational systems, they spread in layers and can continue to grow through time. To understand this shift, the system can be analysed through functional layers such as inputs, memory, reasoning, and execution, while recognising that risk does not remain isolated within these layers but emerges through their interaction.
Agentic AI Attack Surface
A layered view of how risks emerge across input, memory, reasoning, execution, and system integration, including feedback loops and cross-system dependencies that amplify vulnerabilities.
Input Layer: Where Untrusted Data Becomes Control
The entry point of an agent is no longer one prompt. The documents, APIs, files, system logs and the outputs of other agents can now be considered input. This diversity is significant due to the fact that every source of input carries its own trust assumptions, and in the majority of cases, they are weak.
The most obvious threat is prompt injection, where inputs are treated as instructions rather than data. Since inputs are treated as instructions, a virus, a malicious webpage, or a document can contain instructions that override system goals without necessarily being detected as something harmful.
Indirect prompt injection extends this risk beyond direct user interaction. Instead of targeting the interface, attackers compromise the retrieval process by embedding malicious instructions within external data sources. When the agent retrieves and processes the data, it treats the embedded content as legitimate input. As a result, the attack is executed through normal reasoning processes, allowing the system to act on untrusted data without recognising the manipulation.
Data poisoning also occurs at runtime. In contrast to classical poisoning (where training data is manipulated), runtime poisoning distorts the agent’s perception of its environment as it runs. This can change decisions without causing apparent failures.
Obfuscation introduces another indirect attacker vector. Encoded instructions or complicated forms may bypass human review but remain readable to the model. This creates asymmetry whereby the system knows more about the attack than those operating it. Once compromised at this layer, the agent implements compromised instructions which affect downstream operations.
Context and Memory: Persistence of Influence
Agentic systems depend on memory to operate efficiently. They often retain context across sessions and frequently store information between sessions.
This introduces a different type of risk: persistence. Through memory poisoning, attackers can insert false or adversarial information into sorted context, which then influences future decisions. Unlike prompt injection, which is often limited to a single interaction, this effect carries forward. Over time, the agent begins to operate on a distorted internal state, shaping decisions in ways that may not be immediately visible.
Another issue is cross-session leakage. Information in a particular context may be replayed in a different context when memory is being shared or there is insufficient memory separation. This is specifically dangerous in those systems that combine retrieval and long-term storage. The context management in itself becomes a weakness. Agents are required to make decisions on what to retain and what to discard. This is susceptible to attackers who can flood the context or manipulate what is still visible and indirectly affect reasoning.
The underlying problem is structural. Memory turns data into a state. Once state is corrupted, the system cannot easily distinguish valid knowledge from adversarial influence.
The issue is structural. Memory converts temporary data into a persistent state. Once this state is weakened, the system cannot reliably separate valid information from adversarial influence, making recovery significantly more difficult.
Reasoning and Planning: Manipulating Intent Without Breaking Logic
The reasoning layer is where agentic AI stands apart from traditional systems. The model no longer reacts to inputs alone. It actively breaks down objectives, analyses alternatives, and ranks actions.
At the reasoning stage, the nature of risk shifts. The concern is no longer limited to injecting instructions, but to influencing how decisions are made. One example is goal manipulation, where the agent subtly reinterprets its objective and produces outcomes that are technically correct but strategically harmful. Reasoning hijacking operates within intermediate steps, altering how constraints are evaluated or how trade-offs are prioritised. The system may remain internally consistent, which makes such deviations difficult to detect.
Tool selection becomes a critical control point. Agents decide which tools to use and when, so influencing these choices can redirect execution without directly accessing the tools themselves. Hallucinations also take on a different role here. In static systems, they remain errors. In agentic systems, they can trigger actions. A perceived need or incorrect judgement can translate into real-world consequences.
This layer introduces probabilistic failure. The system is not fully weakened, but it is nudged towards decisions that appear reasonable yet are incorrect. The risk lies in how those decisions are justified.
Tool and Execution: When Decisions Gain Reach
Once an agent begins interacting with tools, its behaviour extends beyond the model into external systems. APIs, databases, and services become part of the execution path.
One key risk is the use of unauthorised tools. When agents operate with broad permissions, any manipulation of the upstream can be converted into real-world actions. This makes access control a central security concern. Command injection also takes a different form here. The agent generates commands based on its reasoning, so if that reasoning is compromised, the resulting actions may still appear valid despite being harmful.
External tool outputs introduce another risk. If these systems return corrupted or misleading data, the agent may accept it without verification and incorporate it into its decisions. It is also becoming increasingly reliant on third-part tools and plugins adds to this exposure. If these components are compromised, they can affect behaviour without directly attacking the core system, creating a supply-side risk.
At this stage, the agent effectively operates as an insider. It holds legitimate credentials and interacts with systems in expected ways, making misuse harder to identify.
Application and Integration: System-Level Exposure
Agentic systems rarely operate in isolation. They are embedded in larger environments, interacting with identity systems, business logic, and operational workflows.
Access control becomes a major vulnerability. Agents tend to operate across multiple systems with various permission models, creating irregularities that can be exploited. Risks also arise from identity and delegation. In case an agent is operating on behalf of a user, then any vulnerabilities in authentication or session management can allow attackers to assume that authority.
Workflow execution amplifies these risks. Agents can initiate multi-step processes such as transactions, updates, or approvals. Manipulating a single step can change the result of the entire workflow. As integrations increase, so do the number of interaction points, making cumulative risk harder to track.
At this layer, failures are not isolated. They propagate into business operations, making consequences harder to contain.
Output and Action: Where Failures Become Visible
The output layer is where failures become visible, though they rarely originate there.
Data leakage has been a key concern. Agents may disclose information they are allowed to access, especially when tasks boundaries are not clearly defined. Misinformation and unsafe outputs are also important, particularly when outputs directly influence actions or decisions.
Generated code and commands introduce execution risk. If outputs are used without validation, errors or manipulations can have system-level effects. The shift towards autonomous action increases this risk, as small upstream deviations can lead to significant consequences without human intervention. This layer reflects symptoms rather than root causes. Addressing it alone does not reduce the underlying risk.
Beyond Layers: The Missing Dimension
A layered view helps, but it does not capture the full picture. Agentic systems are defined by continuous interaction across layers.
The key missing dimension is the runtime loop. Inputs shape reasoning, reasoning drives action, and actions feed back into both reasoning and memory. These cycles create feedback loops, where small manipulations may escalate over time. This also reduces observability. With multiple interacting components, it becomes difficult to trace cause and effect or identify where failures originate.
Supply chain dependencies add another layer of risk. Models, datasets, APIs, and plugins each introduce their own points of failure. A compromise at any of these points can propagate across the system. The attack surface also includes governance. Weak supervision, unclear responsibility, or excessive autonomy increase overall risk. Human control is not external to the system; it is part of its security.
Conclusion: Structuring the Attack Surface
Agentic AI expands the attack surface beyond traditional systems. It is both recursive and stateful. Risk does not just accumulate across layers; it moves and changes as the system operates.
Any useful representation must go beyond a linear stack. It should capture feedback loops, persistent state, and cross-layer dependencies that characterise the way these systems actually behave. The system is not a pipeline but a cycle. That is where both its capability and its risk emerge.
Executive Summary
A video allegedly showing Bollywood actor Shah Rukh Khan supporting and expressing his intention to join the so-called ‘Cockroach Janta Party’ (CJP) is being widely shared on social media.In the viral clip, Shah Rukh Khan can allegedly be heard saying:“Friends, the common people of this country are now fully awakened, and the storm of Cockroach Janta Party on social media has become so huge that its name is echoing everywhere… In just a few days, it has gained more than 15 million followers on Instagram… and honestly, I too will soon join the Cockroach Janta Party…”
However, CyberPeace Research Wing investigation found the claim to be false. The voice heard in the viral clip is AI-generated.
Claim
The viral video is being shared with the claim that actor Shah Rukh Khan publicly endorsed the ‘Cockroach Janta Party’ (CJP) and announced that he would soon join the movement.
- https://archive.is/wWueV
Fact Check
To verify the authenticity of the viral video, we first searched the internet using relevant keywords. However, we found no credible media reports, interviews, or posts from Shah Rukh Khan’s official social media accounts mentioning any support for the ‘Cockroach Janta Party’. Notably, if a major actor like Shah Rukh Khan had publicly supported any political or social media movement, it would have received widespread media coverage.
We then analysed key frames from the viral clip using Google Lens. During the investigation, we found an original video uploaded on September 10, 2023, on the YouTube channel of Sri Gokulam Movies. The footage was from the audio launch event of the film Jawan, where Shah Rukh Khan appeared in the same outfit seen in the viral clip.
वीडियो के डिस्क्रिप्शन में लिखा गया है, “शाहरुख़ In the original video, Shah Rukh Khan is seen speaking about the film, its cast, music, and his experience during the event. At no point does he mention the ‘Cockroach Janta Party’. The video description states that Shah Rukh Khan and the film’s team attended the audio launch event of Jawan in Chennai, where he praised music composer Anirudh Ravichander and thanked artists from the Tamil film industry. Additionally, the online trend related to the ‘Cockroach Janta Party’ emerged only in May 2026, whereas the original video is nearly three years old.
During the investigation, we also found several media reports covering the Jawan audio launch event, showing Shah Rukh Khan in the same attire as seen in the viral clip. For instance, a report published by Hindustan Times extensively covered the Chennai event, confirming that the viral footage was taken from the promotional event of the film.
To further examine the audio in the viral clip, we analysed it using the AI detection tool Resemble AI. The tool flagged the voice in the video as likely fake and AI-generated.
Conclusion
The investigation clearly shows that the claim about Shah Rukh Khan supporting or joining the ‘Cockroach Janta Party’ (CJP) is false. The viral video is actually from the 2023 audio launch event of the film Jawan, while the audio added to the clip has been generated using AI.
